rea-agents 6.3.0 → 6.5.0

package/bridge/mitmproxy/capture.py

@@ -6,11 +6,13 @@ The containing mitmdump process and its configuration directory are REA-owned.
 
 import base64
 import hashlib
+import ipaddress
 import json
 import math
 import re
 import resource
 from pathlib import Path
+from urllib.parse import unquote_to_bytes
 
 from mitmproxy import ctx, version
 from mitmproxy.io import tnetstring
@@ -41,6 +43,167 @@ class BoundedReader:
         return self.handle.read(count)
 
 
+SPECIAL_SCHEMES = {"ftp", "file", "http", "https", "ws", "wss"}
+SCHEME_PREFIX = r"^[\x00-\x20]*([a-z][a-z0-9+.-]*):"
+NETWORK_PREFIX = r"^[\x00-\x20]*[/\\]{2}"
+URL_IGNORABLE_CONTROLS = "\t\n\r"
+URL_CONTROL_TRANSLATION = {ord(char): None for char in URL_IGNORABLE_CONTROLS}
+C0_CONTROL_OR_SPACE = "".join(chr(code) for code in range(0x21))
+FORBIDDEN_DOMAIN_CODE_POINTS = set(C0_CONTROL_OR_SPACE) | set("#%/:<>?@[\\]^|\x7f")
+
+
+def authority_start(text, base_scheme=None):
+    """Return where an authority begins and whether it is special, or None.
+
+    Follows WHATWG URL parsing as src/domain/recordedTransportUrl.ts does:
+    special schemes (and scheme-relative references) skip every leading "/"
+    or "\\" before the authority, so `https://\\user:pass@host` still has
+    userinfo. File URLs never carry userinfo: an "@" in a file host makes
+    WHATWG reject the whole URL, so there are no credentials to remove.
+    """
+    scheme = re.match(SCHEME_PREFIX, text, flags=re.I)
+    name = scheme.group(1).lower() if scheme is not None else None
+    if name == "file" or (name is None and base_scheme == "file"):
+        return None
+    if name is not None and name in SPECIAL_SCHEMES:
+        # A same-scheme Location without two slash-equivalent separators is
+        # relative to the recorded request, so its @ belongs to the path.
+        following = text[scheme.end():scheme.end() + 2]
+        if name == base_scheme and (len(following) < 2 or any(char not in "/\\" for char in following)):
+            return None
+        start = scheme.end()
+    else:
+        if scheme is not None:
+            if text[scheme.end():scheme.end() + 2] != "//":
+                return None
+            return scheme.end() + 2, False
+        # A non-special base treats backslashes as authority data and only
+        # recognizes two forward slashes as a network reference.
+        if base_scheme is not None and base_scheme not in SPECIAL_SCHEMES:
+            prefix = re.match(r"^[\x00-\x20]*//", text)
+            return None if prefix is None else (prefix.end(), False)
+        prefix = re.match(NETWORK_PREFIX, text)
+        if prefix is None:
+            return None
+        start = prefix.end()
+    while start < len(text) and text[start] in "/\\":
+        start += 1
+    return start, True
+
+
+IPV4_DIGITS = {8: "01234567", 10: "0123456789", 16: "0123456789abcdefABCDEF"}
+
+
+def ipv4_number(part):
+    """WHATWG IPv4 number parser: decimal, 0x hex or 0-prefixed octal, else None."""
+    if part == "":
+        return None
+    radix, digits = 10, part
+    if part[:2] in ("0x", "0X"):
+        radix, digits = 16, part[2:]
+    elif len(part) > 1 and part[0] == "0":
+        radix, digits = 8, part[1:]
+    if digits == "":
+        return 0
+    if any(char not in IPV4_DIGITS[radix] for char in digits):
+        return None
+    # Bound decimal text before int(): Python limits decimal conversions to
+    # 4300 digits, and anything past 10 significant digits exceeds IPv4.
+    significant = digits.lstrip("0")
+    if radix == 10 and len(significant) > 10:
+        return 2**32
+    return int(digits, radix)
+
+
+def domain_parses(domain):
+    """Apply WHATWG's ends-in-a-number check and IPv4 parser to a domain."""
+    parts = domain.split(".")
+    if parts[-1] == "" and len(parts) > 1:
+        parts.pop()
+    last = parts[-1]
+    if not ((last != "" and last.isascii() and last.isdigit()) or ipv4_number(last) is not None):
+        return True
+    numbers = [ipv4_number(part) for part in parts]
+    if len(parts) > 4 or any(number is None for number in numbers):
+        return False
+    return all(number <= 255 for number in numbers[:-1]) and numbers[-1] < 256 ** (5 - len(numbers))
+
+
+def special_host_parses(host_port):
+    """Whether WHATWG could accept a special authority's host and port.
+
+    A rejected host fails the whole URL, so it has no credentials to remove.
+    This mirrors the forbidden-code-point, empty-host, IPv4, IPv6 and port
+    rules for ASCII hosts. UTS #46 mapping is not modeled: a non-ASCII host
+    may map to an accepted one (fullwidth digits, ideographic full stops,
+    ignored code points), so it is treated as accepted and still redacts.
+    """
+    if host_port.startswith("["):
+        host_end = host_port.find("]") + 1
+        literal = host_port[1 : host_end - 1]
+        if host_end == 0 or "%" in literal:
+            return False
+        try:
+            ipaddress.IPv6Address(literal)
+        except ValueError:
+            return False
+    else:
+        colon = host_port.find(":")
+        host_end = len(host_port) if colon < 0 else colon
+        host = unquote_to_bytes(host_port[:host_end]).decode("utf-8", errors="replace")
+        # Mapping never removes ASCII, so these rejections hold either way.
+        if host == "" or any(char in FORBIDDEN_DOMAIN_CODE_POINTS for char in host):
+            return False
+        if host.isascii() and not domain_parses(host.lower()):
+            return False
+    port = host_port[host_end:]
+    if port == "":
+        return True
+    digits = port[1:]
+    if port[0] != ":" or not (digits == "" or (digits.isascii() and digits.isdigit())):
+        return False
+    # Bound the text first: int() refuses decimal strings over 4300 digits.
+    significant = digits.lstrip("0")
+    return len(significant) <= 5 and int(significant or "0") <= 65535
+
+
+def without_userinfo(value, base_scheme=None):
+    """Remove an authority's userinfo using the WHATWG authority boundary.
+
+    Special schemes and scheme-relative references also end the authority
+    at a backslash, so later path text containing "@" is not userinfo.
+    """
+    binary = isinstance(value, bytes)
+    text = value.decode("latin-1") if binary else value
+    # WHATWG removes these controls before interpreting scheme/separators.
+    # Keep that parse view separate from the exact source spelling and bytes.
+    # It also drops trailing C0 controls and spaces; offsets are unchanged.
+    parsed_text = text.translate(URL_CONTROL_TRANSLATION).rstrip(C0_CONTROL_OR_SPACE)
+    located = authority_start(parsed_text, base_scheme)
+    if located is None:
+        return value
+    start, special = located
+    terminators = "/?#\\" if special else "/?#"
+    end = start
+    while end < len(parsed_text) and parsed_text[end] not in terminators:
+        end += 1
+    at = parsed_text.rfind("@", start, end)
+    if at < start or (special and not special_host_parses(parsed_text[at + 1 : end])):
+        return value
+    parsed_offset = 0
+    raw_start = 0
+    for raw_offset, char in enumerate(text):
+        if char in URL_IGNORABLE_CONTROLS:
+            continue
+        if parsed_offset == start:
+            raw_start = raw_offset
+        if parsed_offset == at:
+            safe = text[:raw_start] + text[raw_offset + 1 :]
+            return safe.encode("latin-1") if binary else safe
+        parsed_offset += 1
+    raise CaptureFailure("decoder", "Normalized URL authority could not be bound to its source.")
+
+
 def project_record(state, secrets):
     binaries, numbers, redactions = [], [], []
     byte_secrets = []
@@ -58,16 +221,23 @@ def project_record(state, secrets):
             return None
         return text
 
-    def transport_value(value, path, transport_url):
+    def transport_value(value, path, transport_url, base_scheme):
         if not (transport_url or re.fullmatch(r"/(?:backup/)*request/(?:path|authority)", path)):
             return value, False
         binary = isinstance(value, bytes)
-        pattern = rb"^([\x00-\x20]*(?:[a-z][a-z0-9+.-]*:)?//)[^/?#]*@" if binary else r"^([\x00-\x20]*(?:[a-z][a-z0-9+.-]*:)?//)[^/?#]*@"
-        replacement = rb"\1" if binary else r"\1"
         separator = b"@" if binary else "@"
-        safe_url = re.sub(pattern, replacement, value, flags=re.I)
-        if path.endswith("/authority") and separator in safe_url:
-            safe_url = safe_url.rsplit(separator, 1)[1]
+        if transport_url:
+            safe_url = without_userinfo(value, base_scheme)
+        elif path.endswith("/authority"):
+            safe_url = value.rsplit(separator, 1)[-1]
+        else:
+            # Native request.path is origin-form unless it explicitly carries
+            # a scheme (absolute-form). Leading separators are path evidence,
+            # not a header URL reference's network authority.
+            text = value.decode("latin-1") if binary else value
+            safe_url = without_userinfo(value) if re.match(
+                SCHEME_PREFIX, text.translate(URL_CONTROL_TRANSLATION), flags=re.I
+            ) else value
         changed = safe_url != value
         if changed:
             redactions.append({"pointer": path, "reason": "transport-credential"})
@@ -80,7 +250,7 @@ def project_record(state, secrets):
         del numbers[before[1]:]
         del redactions[before[2]:]
 
-    def visit(value, path, depth=0, credential=False, transport_url=False):
+    def visit(value, path, depth=0, credential=False, transport_url=False, base_scheme=None):
         if depth > 64:
             raise CaptureFailure("input-limit", "Native capture exceeds the 64-level evidence nesting budget.", path)
         if credential:
@@ -90,10 +260,10 @@ def project_record(state, secrets):
                 binaries.append({"pointer": path, "representation": "producer-bytes", "state": "redacted", "content_base64": None, "bytes": None, "sha256": None})
             return None
         if isinstance(value, bytes):
-            safe_bytes, credential_url = transport_value(value, path, transport_url)
+            safe_bytes, credential_url = transport_value(value, path, transport_url, base_scheme)
             content_base64 = base64.b64encode(value).decode("ascii")
             digest = hashlib.sha256(value).hexdigest()
-            hidden = any(secret in value or secret in safe_bytes for secret in byte_secrets) or any(secret in content_base64 or secret in digest for secret in secrets)
+            hidden = any(secret in value or secret in safe_bytes for secret in byte_secrets) or any(secret in content_base64 or secret in digest or secret in str(len(value)) for secret in secrets)
             safe_text = None
             try:
                 safe_text = safe_bytes.decode("utf-8", errors="strict")
@@ -107,7 +277,7 @@ def project_record(state, secrets):
                 return None
             return safe_text
         if isinstance(value, str):
-            safe_text, _ = transport_value(value, path, transport_url)
+            safe_text, _ = transport_value(value, path, transport_url, base_scheme)
             return redact(safe_text, path, value)
         if isinstance(value, bool) or value is None:
             return value
@@ -125,10 +295,16 @@ def project_record(state, secrets):
                 for index, field in enumerate(value):
                     if not isinstance(field, (list, tuple)) or len(field) != 2 or not isinstance(field[0], bytes):
                         raise CaptureFailure("format", "Native header/trailer is not an ordered byte pair.", pointer(path, index))
-                    result.append([visit(field[0], pointer(pointer(path, index), 0), depth + 2), visit(field[1], pointer(pointer(path, index), 1), depth + 2, field[0].lower() in CREDENTIALS, field[0].lower() in {b"location", b"referer", b"origin"})])
+                    result.append([visit(field[0], pointer(pointer(path, index), 0), depth + 2), visit(field[1], pointer(pointer(path, index), 1), depth + 2, field[0].lower() in CREDENTIALS, field[0].lower() in {b"location", b"referer", b"origin"}, base_scheme if field[0].lower() == b"location" else None)])
                 return result
-            return [visit(item, pointer(path, index), depth + 1) for index, item in enumerate(value)]
+            return [visit(item, pointer(path, index), depth + 1, base_scheme=base_scheme) for index, item in enumerate(value)]
         if isinstance(value, dict):
+            if path == "" or re.fullmatch(r"/backup(?:/backup)*", path):
+                request = value.get("request")
+                scheme = request.get("scheme") if isinstance(request, dict) else None
+                if isinstance(scheme, bytes):
+                    scheme = scheme.decode("latin-1")
+                base_scheme = scheme.lower() if isinstance(scheme, str) and re.fullmatch(r"[a-z][a-z0-9+.-]*", scheme, flags=re.I) else None
             result = {}
             for key, item in value.items():
                 if not isinstance(key, str):
@@ -139,7 +315,7 @@ def project_record(state, secrets):
                     validate_omitted(item, pointer(path, key), depth + 1)
                     redactions.append({"pointer": path, "reason": "explicit-sensitive-value", "scope": "property-name"})
                     continue
-                result[key] = visit(item, pointer(path, key), depth + 1)
+                result[key] = visit(item, pointer(path, key), depth + 1, base_scheme=base_scheme)
             return result
         raise CaptureFailure("decoder", "Native parser returned an unexpected value type: " + type(value).__name__ + ".", path)
 

package/bridge/native/rea_lldb_tracer.py

@@ -567,18 +567,27 @@ def trace(debugger, config):
         before_digest = _hash_file(config["executable"])
         before_identity = _file_identity(config["executable"])
     except OSError as error:
-        return {"status": "target-integrity-error", "error": str(error)}
+        return {
+            "status": "target-integrity-error",
+            "error": str(error),
+            "target_process_created": False,
+        }
     if before_digest != config["expected_sha256"]:
         return {
             "status": "target-integrity-error",
             "error": "selected executable digest changed before LLDB target creation",
+            "target_process_created": False,
         }
     error = lldb.SBError()
     target = debugger.CreateTarget(
         config["executable"], config["architecture"], None, False, error
     )
     if not target.IsValid():
-        return {"status": "target-error", "error": error.GetCString()}
+        return {
+            "status": "target-error",
+            "error": error.GetCString(),
+            "target_process_created": False,
+        }
     module_path_before, module_file_identity_before, module_uuid_before = (
         _module_identity(target)
     )
@@ -589,6 +598,7 @@ def trace(debugger, config):
         return {
             "status": "target-integrity-error",
             "error": "LLDB executable module resolved to a different pre-launch file identity",
+            "target_process_created": False,
         }
     created = [_create_breakpoints(target, spec) for spec in config["breakpoints"]]
     breakpoint_index = {}
@@ -622,12 +632,24 @@ def trace(debugger, config):
         if not error.Success() or not process.IsValid():
             stdout.close()
             stderr.close()
-            return {"status": "launch-error", "error": error.GetCString()}
+            return {
+                "status": "launch-error",
+                "error": error.GetCString(),
+                **(
+                    {"target_process_created": True}
+                    if process.IsValid()
+                    else {}
+                ),
+            }
         launch_failure = _failed_launch_description(process)
         if launch_failure is not None:
             stdout.close(expected_exit=True)
             stderr.close(expected_exit=True)
-            return {"status": "launch-error", "error": launch_failure}
+            return {
+                "status": "launch-error",
+                "error": launch_failure,
+                "target_process_created": True,
+            }
         stdout.mark_launched()
         stderr.mark_launched()
         # Publish the PID before any post-launch file or module inspection. The
@@ -644,6 +666,7 @@ def trace(debugger, config):
             return {
                 "status": "target-identity-unavailable",
                 "error": "host could not establish the launched process identity; target was stopped",
+                "target_process_created": True,
             }
         try:
             after_digest = _hash_file(config["executable"])
@@ -652,7 +675,11 @@ def trace(debugger, config):
             process.Kill()
             stdout.close(expected_exit=process.GetState() == lldb.eStateExited)
             stderr.close(expected_exit=process.GetState() == lldb.eStateExited)
-            return {"status": "target-integrity-error", "error": str(identity_error)}
+            return {
+                "status": "target-integrity-error",
+                "error": str(identity_error),
+                "target_process_created": True,
+            }
         if after_digest != config["expected_sha256"] or after_identity != before_identity:
             process.Kill()
             _wait_for_exit(listener, process, 5)
@@ -661,6 +688,7 @@ def trace(debugger, config):
             return {
                 "status": "target-integrity-error",
                 "error": "selected executable digest or file identity changed during LLDB launch",
+                "target_process_created": True,
             }
         module_path_after, module_file_identity_after, module_uuid_after = (
             _module_identity(target)
@@ -676,6 +704,7 @@ def trace(debugger, config):
             return {
                 "status": "target-integrity-error",
                 "error": "LLDB executable module resolved to a different file identity",
+                "target_process_created": True,
             }
         if (
             module_uuid_before is not None
@@ -689,6 +718,7 @@ def trace(debugger, config):
             return {
                 "status": "target-integrity-error",
                 "error": "LLDB executable module identity changed during launch",
+                "target_process_created": True,
             }
         context = {
             "target": target,
@@ -748,7 +778,11 @@ def trace(debugger, config):
         # exit code; preserve the debugger's concrete launch denial.
         launch_failure = _failed_launch_description(process)
         if launch_failure is not None:
-            return {"status": "launch-error", "error": launch_failure}
+            return {
+                "status": "launch-error",
+                "error": launch_failure,
+                "target_process_created": True,
+            }
         launch_identity_stable = (
             module_path_before is not None
             and module_path_after == module_path_before

package/bridge/process/ProcessRunTokenReader.swift

@@ -112,6 +112,11 @@ enum RunTokenReadError: Error {
   case ambiguousEnvironmentBoundary
 }
 
+struct ParsedRunToken {
+  let runId: String?
+  let environmentEntryCount: Int
+}
+
 @_silgen_name("csops")
 private func csops(
   _ pid: Int32,
@@ -122,19 +127,67 @@ private func csops(
 
 private let csOpsStatus: UInt32 = 0
 private let csPlatformBinary: UInt32 = 0x0400_0000
+private let csRestrict: UInt32 = 0x0000_0800
 
-/**
- * Whether the target image is an Apple platform binary. Current macOS omits
- * the environment of platform binaries from KERN_PROCARGS2 for every caller,
- * so this distinguishes a policy-withheld environment from a process whose
- * environment is genuinely absent or transiently unreadable.
- */
-func isPlatformBinary(pid: Int32) -> Bool {
+/** Read the target's current code-signing flags when csops permits inspection. */
+private func codeSigningFlags(pid: Int32) -> UInt32? {
   var flags: UInt32 = 0
   let result = withUnsafeMutablePointer(to: &flags) { pointer in
     csops(pid, csOpsStatus, UnsafeMutableRawPointer(pointer), MemoryLayout<UInt32>.size)
   }
-  return result == 0 && (flags & csPlatformBinary) != 0
+  return result == 0 ? flags : nil
+}
+
+/** Derive one process-token observation from parser facts and native flags. */
+func processRunTokenObservation(
+  pid: Int32,
+  parse: Result<ParsedRunToken, RunTokenReadError>,
+  codeSigningFlags: () -> UInt32?
+) -> RunTokenObservation {
+  switch parse {
+  case .success(let parsed):
+    if let runId = parsed.runId {
+      return RunTokenObservation(pid: pid, state: "readable", run_id: runId, reason: nil)
+    }
+    // A non-empty environment without REA's token proves this candidate is
+    // unrelated. CS_RESTRICT cannot turn that readable fact into uncertainty.
+    if parsed.environmentEntryCount > 0 {
+      return RunTokenObservation(pid: pid, state: "readable", run_id: nil, reason: nil)
+    }
+    let flags = codeSigningFlags()
+    if let flags, (flags & csPlatformBinary) != 0 {
+      return unavailable(pid: pid, reason: "platform_binary_environment_withheld")
+    }
+    if let flags, (flags & csRestrict) != 0 {
+      return unavailable(pid: pid, reason: "restricted_process_environment_withheld")
+    }
+    return RunTokenObservation(pid: pid, state: "readable", run_id: nil, reason: nil)
+  case .failure(let failure):
+    switch failure {
+    case .environmentUnavailable:
+      let flags = codeSigningFlags()
+      if let flags, (flags & csPlatformBinary) != 0 {
+        return unavailable(pid: pid, reason: "platform_binary_environment_withheld")
+      }
+      if let flags, (flags & csRestrict) != 0 {
+        return unavailable(pid: pid, reason: "restricted_process_environment_withheld")
+      }
+      return unavailable(pid: pid, reason: "environment_unavailable")
+    case .ambiguousEnvironmentBoundary:
+      if let flags = codeSigningFlags(), (flags & csRestrict) != 0 {
+        return unavailable(pid: pid, reason: "restricted_process_environment_withheld")
+      }
+      return unavailable(pid: pid, reason: "ambiguous_environment_boundary")
+    case .duplicateToken:
+      return unavailable(pid: pid, reason: "duplicate_run_token")
+    case .invalidTokenEncoding:
+      return unavailable(pid: pid, reason: "invalid_run_token_encoding")
+    case .appleVectorUnavailable:
+      return unavailable(pid: pid, reason: "apple_vector_unavailable")
+    case .invalidBuffer:
+      return unavailable(pid: pid, reason: "malformed_procargs")
+    }
+  }
 }
 
 private func readRunToken(pid: Int32, pointerSize: Int) -> RunTokenObservation {
@@ -151,33 +204,19 @@ private func readRunToken(pid: Int32, pointerSize: Int) -> RunTokenObservation {
     return unavailable(pid: pid, reason: "sysctl_failed_\(errno)")
   }
   bytes = Array(bytes.prefix(size))
+  let parse: Result<ParsedRunToken, RunTokenReadError>
   do {
-    let runId = try token(in: bytes, pointerSize: pointerSize)
-    // A complete empty environment is readable for an ordinary image. Apple
-    // platform images can expose the same layout after the kernel withholds
-    // their environment, so they remain explicitly unverified without a token.
-    if runId == nil && isPlatformBinary(pid: pid) {
-      return unavailable(pid: pid, reason: "platform_binary_environment_withheld")
-    }
-    return RunTokenObservation(pid: pid, state: "readable", run_id: runId, reason: nil)
-  } catch RunTokenReadError.duplicateToken {
-    return unavailable(pid: pid, reason: "duplicate_run_token")
-  } catch RunTokenReadError.invalidTokenEncoding {
-    return unavailable(pid: pid, reason: "invalid_run_token_encoding")
-  } catch RunTokenReadError.environmentUnavailable {
-    return unavailable(
-      pid: pid,
-      reason: isPlatformBinary(pid: pid)
-        ? "platform_binary_environment_withheld"
-        : "environment_unavailable"
-    )
-  } catch RunTokenReadError.appleVectorUnavailable {
-    return unavailable(pid: pid, reason: "apple_vector_unavailable")
-  } catch RunTokenReadError.ambiguousEnvironmentBoundary {
-    return unavailable(pid: pid, reason: "ambiguous_environment_boundary")
+    parse = .success(try parseProcessEnvironment(in: bytes, pointerSize: pointerSize))
+  } catch let failure as RunTokenReadError {
+    parse = .failure(failure)
   } catch {
-    return unavailable(pid: pid, reason: "malformed_procargs")
+    parse = .failure(.invalidBuffer)
   }
+  return processRunTokenObservation(
+    pid: pid,
+    parse: parse,
+    codeSigningFlags: { codeSigningFlags(pid: pid) }
+  )
 }
 
 func readRunTokens(pids: [Int32]) -> [RunTokenObservation] {
@@ -201,7 +240,10 @@ func readRunTokens(pids: [Int32]) -> [RunTokenObservation] {
   }
 }
 
-func token(in bytes: [UInt8], pointerSize: Int = MemoryLayout<UnsafeRawPointer>.size) throws -> String? {
+func parseProcessEnvironment(
+  in bytes: [UInt8],
+  pointerSize: Int = MemoryLayout<UnsafeRawPointer>.size
+) throws -> ParsedRunToken {
   guard bytes.count >= MemoryLayout<Int32>.size else { throw RunTokenReadError.invalidBuffer }
   let argc = bytes.withUnsafeBytes { $0.loadUnaligned(as: Int32.self).littleEndian }
   guard argc >= 0, Int(argc) <= bytes.count else { throw RunTokenReadError.invalidBuffer }
@@ -277,7 +319,7 @@ func token(in bytes: [UInt8], pointerSize: Int = MemoryLayout<UnsafeRawPointer>.
       found = decoded
     }
   }
-  return found
+  return ParsedRunToken(runId: found, environmentEntryCount: environmentEntries.count)
 }
 
 private func readString(

package/bridge/pwntools/layout_impl.py

@@ -206,6 +206,11 @@ def inspect_elf(path, cache):
                             "visibility": raw.st_other.visibility, "section_index": raw.st_shndx,
                         })
                 if h.sh_type in ("SHT_REL", "SHT_RELA"):
+                    if h.sh_size % h.sh_entsize != 0:
+                        raise LayoutFailure(
+                            "format",
+                            f"ELF relocation section {index} size is not a multiple of its {h.sh_entsize}-byte entries.",
+                        )
                     if image.header.e_type == "ET_REL" and h.sh_info >= len(all_sections):
                         raise LayoutFailure("format", f"ELF relocation section {index} references missing target section {h.sh_info}.")
                     symbol_table = None

package/bridge/pwntools/recorded_crash_impl.py

@@ -11,6 +11,12 @@ import sys
 
 PROFILE = "pwntools@4.15.0;pyelftools@0.33;unicorn@2.1.2"
 
+# Linux ET_CORE machine identifiers whose PRSTATUS layout is interpreted with
+# unchanged pwntools 4.15.0 ctypes. Both share pr_cursig@12, pr_pid@32 and
+# pr_reg@112; only the register window differs: amd64 is 27 x 8 bytes for a
+# 336-byte descriptor, AArch64 is 34 x 8 bytes for a 392-byte descriptor.
+CORE_MACHINES = (62, 183)
+
 
 class CoreFailure(Exception):
     def __init__(self, reason, message):
@@ -51,12 +57,27 @@ def inspect_core(path, cache):
     # Other declared OSABIs must never select Linux note ctypes.
     if content[7] not in (0, 3) or content[8] != 0:
         raise CoreFailure("unsupported-target", "Initial recorded-core profile requires System V or GNU/Linux OSABI with ABI version zero; selected OSABI=" + str(content[7]) + ", ABI version=" + str(content[8]) + ".")
-    if int.from_bytes(content[16:18], "little") != 4 or int.from_bytes(content[18:20], "little") != 62:
-        raise CoreFailure("unsupported-target", "Initial recorded-core profile requires x86-64 ET_CORE.")
+    machine = int.from_bytes(content[18:20], "little")
+    if int.from_bytes(content[16:18], "little") != 4 or machine not in CORE_MACHINES:
+        raise CoreFailure("unsupported-target", "Initial recorded-core profile requires ET_CORE for x86-64 or AArch64; selected ET_TYPE=" + str(int.from_bytes(content[16:18], "little")) + ", e_machine=" + str(machine) + ".")
     from elftools.common.exceptions import ELFError
     from elftools.common.utils import struct_parse
     from elftools.elf.elffile import ELFFile
-    from pwnlib.elf.datatypes import elf_prstatus_amd64, elf_siginfo_64, user_regs_struct_amd64
+    from pwnlib.elf.datatypes import (
+        elf_prstatus_aarch64,
+        elf_prstatus_amd64,
+        elf_siginfo_64,
+        user_regs_struct_aarch64,
+        user_regs_struct_amd64,
+    )
+    if machine == 62:
+        profile_label = "x86-64"
+        architecture = "x86_64-little-endian"
+        prstatus_type, registers_type = elf_prstatus_amd64, user_regs_struct_amd64
+    else:
+        profile_label = "AArch64"
+        architecture = "aarch64-little-endian"
+        prstatus_type, registers_type = elf_prstatus_aarch64, user_regs_struct_aarch64
     try:
         image = ELFFile(io.BytesIO(content))
         header = image.header
@@ -107,17 +128,17 @@ def inspect_core(path, cache):
                 if owner != b"CORE\0":
                     continue
                 if note.n_type == "NT_PRSTATUS":
-                    if len(descriptor) < ctypes.sizeof(elf_prstatus_amd64):
-                        raise CoreFailure("format", "Linux amd64 NT_PRSTATUS descriptor is truncated.")
-                    status = elf_prstatus_amd64.from_buffer_copy(descriptor)
+                    if len(descriptor) < ctypes.sizeof(prstatus_type):
+                        raise CoreFailure("format", "Linux " + profile_label + " NT_PRSTATUS descriptor is truncated.")
+                    status = prstatus_type.from_buffer_copy(descriptor)
                     registers = []
-                    for name, kind in user_regs_struct_amd64._fields_:
-                        relative = elf_prstatus_amd64.pr_reg.offset + getattr(user_regs_struct_amd64, name).offset
+                    for name, kind in registers_type._fields_:
+                        relative = prstatus_type.pr_reg.offset + getattr(registers_type, name).offset
                         registers.append({"name": name, "value": hex(getattr(status.pr_reg, name)), "location": location(descriptor_start + relative, ctypes.sizeof(kind), end)})
                     threads.append({"note_index": note_index, "historical_pid": ctypes.c_int32(status.pr_pid).value, "recorded_current_signal": status.pr_cursig, "registers": registers})
                 elif note.n_type == "NT_SIGINFO":
                     if len(descriptor) < ctypes.sizeof(elf_siginfo_64):
-                        raise CoreFailure("format", "Linux amd64 NT_SIGINFO descriptor is truncated.")
+                        raise CoreFailure("format", "Linux " + profile_label + " NT_SIGINFO descriptor is truncated.")
                     signal = elf_siginfo_64.from_buffer_copy(descriptor)
                     number = ctypes.c_int32(signal.si_signo).value
                     code = ctypes.c_int32(signal.si_code).value
@@ -125,7 +146,7 @@ def inspect_core(path, cache):
                     signals.append({"note_index": note_index, "number": number, "code": code, "errno": ctypes.c_int32(signal.si_errno).value,
                                     "fault_address": hex(signal.sigfault_addr) if known else None,
                                     "fault_address_meaning": "recorded-sigsegv-address" if known else "unknown", "thread_association": "unknown"})
-        return {"format": "elf-core", "architecture": "x86_64-little-endian", "target_execution": "not-performed", "live_process_identity": "unknown",
+        return {"format": "elf-core", "architecture": architecture, "target_execution": "not-performed", "live_process_identity": "unknown",
                 "segments": segments, "notes": notes, "note_padding": padding, "threads": threads, "signals": signals,
                 "note_interpretation_completeness": "unknown",
                 "limitations": ["The initial Linux note profile accepts System V/unspecified or GNU/Linux OSABI with ABI version zero; an unspecified OSABI alone does not prove operating-system origin.",