skill-sentinel 0.1.0__tar.gz

skill_sentinel-0.1.0/.gitignore

@@ -0,0 +1,21 @@
+# Secrets
+.env
+
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+*.egg
+dist/
+build/
+*.whl
+
+# IDE
+.vscode/
+.idea/
+.DS_Store
+
+# Reports (generated output)
+report.json
+
+.venv/

skill_sentinel-0.1.0/LICENSE

@@ -0,0 +1,191 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by the Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding any notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2025 Enkrypt AI, Inc.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

skill_sentinel-0.1.0/PKG-INFO

@@ -0,0 +1,302 @@
+Metadata-Version: 2.4
+Name: skill-sentinel
+Version: 0.1.0
+Summary: Scan Agent Skill packages for security threats using multi-agent AI analysis
+Author: Enkrypt AI
+License: Apache-2.0
+License-File: LICENSE
+Keywords: agent,crewai,llm,scanner,security,skill
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Security
+Requires-Python: <3.14,>=3.10
+Requires-Dist: crewai[tools]<2.0,>=1.9
+Requires-Dist: httpx>=0.27
+Requires-Dist: python-dotenv>=1.0
+Description-Content-Type: text/markdown
+
+# <img src="assets/skill-sentinel.png" alt="Skill Sentinel" width="32" style="vertical-align: middle;"> Enkrypt AI Skill Sentinel
+
+A security scanner for Agent Skill packages. Skill Sentinel uses multi-agent AI analysis to detect prompt injection, data exfiltration, command injection, malware, and other threats hiding in skill packages for Cursor, Claude Code, Codex, and OpenClaw.
+
+<div align="center">
+  <img src="assets/skill-sentinel-features.png" width="800" alt="Skill Sentinel">
+</div>
+
+Agent Skills extend AI coding assistants with custom instructions and scripts — but they also create a new attack surface. A single malicious skill can steal credentials, inject hidden prompts, exfiltrate code, or execute arbitrary commands. Skill Sentinel catches these threats before they reach your agent.
+
+### Supported Platforms
+
+<table>
+  <tr>
+    <td align="center" width="120"><img src="assets/cursor.png" alt="Cursor" width="40"><br><b>Cursor</b></td>
+    <td align="center" width="120"><img src="assets/claude.png" alt="Claude Code" width="40"><br><b>Claude Code</b></td>
+    <td align="center" width="120"><img src="assets/codex.png" alt="Codex" width="40"><br><b>Codex</b></td>
+    <td align="center" width="120"><img src="assets/openclaw.png" alt="OpenClaw" width="40"><br><b>OpenClaw</b></td>
+    <td align="center" width="120"><i>and other agents</i></td>
+  </tr>
+</table>
+
+## Key Features
+
+### 🔍 Multi-Agent Security Pipeline
+
+Specialized agents work together to analyze Skills from multiple angles — manifest inspection, file verification, cross-referencing, and threat correlation.
+
+### 🦠 Built-in Malware Detection
+
+Automatic VirusTotal integration scans binary files (executables, archives, PDFs) for known malware before any LLM analysis begins.
+
+### 📄 No Truncation Limits
+
+Reads complete file contents without arbitrary cutoffs — catching malicious instructions hidden deep in documentation where other scanners stop looking.
+
+### 🔗 Cross-File Threat Correlation
+
+Detects sophisticated attacks that span multiple files by tracking data flows and verifying that script behavior matches documented claims.
+
+### 🎯 AI Agent Attack Detection
+
+Purpose-built for prompt injection, command injection, credential theft, and other threats specific to AI coding assistants.
+
+### ⚡ Parallel Bulk Scanning
+
+Scan entire directories of Skills concurrently with organized reports — audit all your Cursor, Claude Code, Codex, and OpenClaw Skills in one command.
+
+## Installation
+
+Requires Python >= 3.10, < 3.14.
+
+### Using uv (recommended)
+
+```bash
+uv venv --python 3.13 .venv
+source .venv/bin/activate
+uv pip install .
+```
+
+### Using pip
+
+```bash
+pip install .
+```
+
+For development (editable mode):
+
+```bash
+uv pip install -e .
+# or
+pip install -e .
+```
+
+## Quick Start
+
+```bash
+# 1. Export your OpenAI API key
+export OPENAI_API_KEY="sk-..."
+
+# 2. (Optional) Export your VirusTotal API key for binary malware scanning
+export VIRUSTOTAL_API_KEY="your-vt-api-key"
+
+# 3. Scan a skill directory
+skill-sentinel scan /path/to/skill/directory
+```
+
+Alternatively, create a `.env` file in the project root instead of exporting variables:
+
+```bash
+cp .env.example .env
+# Edit .env with your keys
+```
+
+## Usage
+
+```
+skill-sentinel scan [provider] [OPTIONS]
+
+Positional:
+  provider              cursor / claude / codex / openclaw to auto-discover that
+                        provider's skills, or omit to discover all.
+                        Can also be a direct path to a skill directory.
+
+Path flags (mutually exclusive):
+  --skill PATH          Scan a single skill directory.
+  --dir PATH            Scan all skill subdirectories inside a parent directory.
+
+Options:
+  -o, --output PATH     Single scan: output file (default: report.json).
+                        Multi-scan: output directory (default: ./skill_sentinel_reports).
+  --parallel            Scan multiple skills in parallel (5 concurrent).
+  -m, --model MODEL     OpenAI model to use (default: gpt-4.1).
+  --api-key KEY         OpenAI API key (prefer OPENAI_API_KEY env var).
+  -V, --version         Show version and exit.
+```
+
+### Examples
+
+```bash
+# Scan a single skill directory
+skill-sentinel scan --skill ./my-skill
+skill-sentinel scan --skill ./my-skill -o report.json
+
+# Scan all skills inside a parent directory
+skill-sentinel scan --dir ./all-my-skills/
+skill-sentinel scan --dir ./all-my-skills/ -o ./reports/
+
+# Scan in parallel (5 concurrent)
+skill-sentinel scan --dir ./all-my-skills/ --parallel
+
+# Auto-discover and scan ALL skills from cursor, claude, codex, and openclaw paths
+skill-sentinel scan
+
+# Auto-discover only Cursor skills, in parallel
+skill-sentinel scan cursor --parallel
+
+# Scan only Claude skills
+skill-sentinel scan claude
+
+# Custom output directory for auto-discovery
+skill-sentinel scan codex -o ./my-reports/
+
+# Use a different model
+skill-sentinel scan --skill ./my-skill -m gpt-4o
+```
+
+### Auto-Discovery
+
+When no path is given (or a provider keyword is used), the scanner searches these well-known locations for skill directories containing a `SKILL.md`:
+
+| Location | Scope |
+|---|---|
+| `.cursor/skills/` | Project-level (Cursor) |
+| `.claude/skills/` | Project-level (Claude) |
+| `.codex/skills/` | Project-level (Codex) |
+| `skills/` | Agent workspace-level (OpenClaw) |
+| `~/.cursor/skills/` | User-level global (Cursor) |
+| `~/.claude/skills/` | User-level global (Claude) |
+| `~/.codex/skills/` | User-level global (Codex) |
+| `~/.openclaw/skills/` | User-level global (OpenClaw) |
+
+Reports are saved as `<provider>__<skill_name>.json` in `./skill_sentinel_reports/` (or the directory specified with `-o`).
+
+### Programmatic Usage
+
+```python
+from skill_sentinel.main import scan
+
+report = scan("/path/to/skill", output_path="report.json", model="gpt-4.1")
+print(report["overall_risk_assessment"]["skill_verdict"])
+```
+
+## What It Does
+
+The scanner performs a multi-step security analysis:
+
+1. **File Discovery** — lists all files in the skill directory (static, no LLM).
+2. **VirusTotal Binary Scan** *(optional)* — if binary files (executables, archives, images, PDFs, etc.) are found and a `VIRUSTOTAL_API_KEY` is set, each binary is checked against VirusTotal's malware database via SHA-256 hash lookup. Results are passed to the report synthesizer.
+3. **SKILL.md Analysis** — an agent reads the SKILL.md manifest and instructions, looking for prompt injection, trust abuse, discovery abuse, and other threats.
+4. **File Verification** *(conditional)* — if the skill contains scripts or referenced files beyond SKILL.md, a second agent reads each file and checks alignment with SKILL.md claims, searching for command injection, data exfiltration, hardcoded secrets, obfuscation, etc.
+5. **Report Synthesis** — a final agent combines all findings (including VirusTotal results), filters false positives, prioritizes findings, and produces a structured JSON report.
+
+### Malware Scanning (VirusTotal)
+
+If a `VIRUSTOTAL_API_KEY` environment variable is set, Skill Sentinel automatically scans binary files found in skill packages against VirusTotal's malware database. This runs **before** the agent pipeline — no LLM calls are needed.
+
+**Supported binary types:** executables (`.exe`, `.dll`, `.so`, `.dylib`, `.bin`), archives (`.zip`, `.tar`, `.gz`, `.7z`, `.rar`), documents (`.pdf`, `.doc`, `.xls`), images (`.png`, `.jpg`, `.gif`), JVM/WASM (`.jar`, `.war`, `.wasm`, `.class`), and more.
+
+**Getting a free API key:** Sign up at [virustotal.com](https://www.virustotal.com/) — the free tier allows 500 lookups/day, which is more than enough for skill scanning.
+
+## Output
+
+The scanner writes a JSON report containing:
+
+- `skill_path` — absolute path to the scanned skill directory
+- `validated_findings` — confirmed threats with severity, evidence, remediation
+- `false_positives` — dismissed findings with reasoning
+- `priority_order` — ranked list of finding IDs
+- `correlations` — related findings grouped together
+- `recommendations` — actionable next steps
+- `references` — VirusTotal scan links and other reference URLs
+- `overall_risk_assessment` — risk level, verdict (SAFE / SUSPICIOUS / MALICIOUS), reasoning
+- `token_usage` — LLM token usage metrics for the scan
+
+## Project Structure
+
+```
+skill_scanner_package/
+├── pyproject.toml              # Package build config
+├── README.md
+└── src/skill_sentinel/
+    ├── __init__.py             # Package version
+    ├── cli.py                  # CLI entry point
+    ├── main.py                 # Programmatic API
+    ├── crew.py                 # Multi-agent crew definition
+    ├── config/
+    │   ├── agents.yaml         # Agent definitions
+    │   └── tasks.yaml          # Task definitions
+    ├── data/
+    │   ├── threat_categories.md    # Threat taxonomy
+    │   └── report_schema.json      # Output JSON schema
+    └── tools/
+        ├── custom_tool.py      # ReadFile & Grep tools
+        ├── file_discovery.py   # Static file listing
+        └── virustotal_tool.py  # VirusTotal binary malware scanning
+```
+
+## Environment Variables
+
+| Variable | Description | Default |
+|---|---|---|
+| `OPENAI_API_KEY` | Your OpenAI API key (required) | — |
+| `OPENAI_MODEL_NAME` | Model to use for analysis | `gpt-4.1` |
+| `VIRUSTOTAL_API_KEY` | VirusTotal API key for binary malware scanning (optional) | — |
+
+## Threat Categories
+
+Skill Sentinel detects the following threat categories, mapped to [OWASP Top 10 for LLM Applications 2025](https://genai.owasp.org/llm-top-10/) and [OWASP Top 10 for Agentic Applications](https://genai.owasp.org/agentic-top-10/):
+
+| Category | Severity | Description |
+|---|---|---|
+| Prompt Injection | HIGH–CRITICAL | Override attempts, mode changes, policy bypass hidden in SKILL.md |
+| Transitive Trust Abuse | HIGH | Instructions that delegate trust to external/untrusted data sources |
+| Data Exfiltration | CRITICAL | Network calls that steal credentials, files, or environment variables |
+| Command Injection | CRITICAL | Dangerous `eval()`, `exec()`, `os.system()`, shell injection |
+| Hardcoded Secrets | CRITICAL | API keys, passwords, private keys embedded in code |
+| Obfuscation | HIGH | Base64 blobs + exec, hex-encoded payloads, deliberately unreadable code |
+| Unauthorized Tool Use | HIGH | Code that violates the skill's own `allowed-tools` declaration |
+| Skill Discovery Abuse | HIGH | Brand impersonation, keyword baiting, misleading descriptions |
+| Tool Chaining Abuse | HIGH | Multi-step workflows that read sensitive data then transmit it |
+| Resource Abuse | MEDIUM | Infinite loops, unbounded memory allocation, recursive bombs |
+| Autonomy Abuse | MEDIUM | Unsolicited activation, unbounded retries, no user confirmation |
+| Over-Collection | MEDIUM | Disproportionate data access relative to stated purpose |
+| Cross-Context Bridging | MEDIUM | Accessing data from other sessions, conversations, or workspaces |
+| Dependency Risk | MEDIUM | Unpinned `pip install`, typosquatting, unknown GitHub repos |
+| Malware | MEDIUM–CRITICAL | Binary files flagged by VirusTotal or unverifiable binaries |
+
+## Contributing
+
+Contributions are welcome! To get started:
+
+1. Fork the repository
+2. Create a feature branch (`git checkout -b feature/my-feature`)
+3. Set up the development environment:
+
+```bash
+uv venv --python 3.13 .venv
+source .venv/bin/activate
+uv pip install -e .
+```
+
+4. Make your changes
+5. Submit a pull request
+
+## License
+
+This project is licensed under the [Apache License 2.0](LICENSE).
+
+Copyright 2025 [Enkrypt AI, Inc.](https://www.enkryptai.com/)