nsauditor-ai-agent-skill 0.1.60 → 0.1.62

package/CHANGELOG.md

@@ -4,6 +4,10 @@ Release notes for **`nsauditor-ai-agent-skill`** — installable knowledge packa
 
 ---
 
+## 0.1.62 (2026-05-30) — Paired-release pin for EE 0.16.3 + CE 0.1.94 — MCP `scan_cloud` now runs its cloud plugins concurrently with a per-plugin timeout (`CLOUD_SCAN_CONCURRENCY` / `CLOUD_PLUGIN_TIMEOUT_MS`), so a full AWS/GCP/Azure account audit finishes within Claude Desktop's ~60s tool-call limit. Internal CE engine change; no tool surface or behavior change for the agent. Plugin count UNCHANGED (28); all six matrices UNCHANGED. SKILL.md/references unchanged.
+
+## 0.1.61 (2026-05-30) — **HOTFIX: SKILL.md `description` trimmed to fit the 1024-char skill-upload limit.** The frontmatter `description` had grown to 1241 chars, so Claude Desktop rejected the skill upload (`field 'description' in SKILL.md must be at most 1024 characters`). Rewrote it to 967 chars while keeping the high-value trigger keywords and adding the new cloud-audit triggers (`scan_cloud`, "audit my AWS/GCP/Azure account", "cloud compliance"). No body/content change vs 0.1.60 (still teaches `scan_cloud`); pairs the same EE 0.16.2 + CE 0.1.93.
+
 ## 0.1.60 (2026-05-30) — Paired-release for EE 0.16.2 + CE 0.1.93 — **SKILL.md updated**: teaches the NEW MCP `scan_cloud` tool (audit AWS/GCP/Azure accounts directly, no network host) — added to the Pro/Enterprise Tools table (Enterprise tier) + the "which tool to use" decision tree, plus a result-interpretation rule ("a cloud was effectively audited only if it's in `auditedProviders`; `audited:false` / `notes` / `pluginsRan:0` means NOT audited — never report a clean pass"). Feature lives in CE 0.1.93; plugin count UNCHANGED (28); all six matrices UNCHANGED.
 
 ## 0.1.59 (2026-05-30) — Paired-release pin for EE 0.16.1 + CE 0.1.92 — MCP `NSA_ENV_FILE`: the MCP server now loads a per-environment dotenv file named by `NSA_ENV_FILE` at startup (the MCP analog of the 0.16.0 CLI `--env`), so an operator points the server at a specific account/cloud by changing one path in the Claude Desktop / Claude Code config. Loaded after auth + license (scan-target vars only); fail-fast + authoritative-file ambient-cred clearing close a false-clean caught by the `audit-cloud-plugin-false-negatives` review. Feature lives in CE; plugin count UNCHANGED (28); all six matrices UNCHANGED. SKILL.md/references unchanged.

package/SKILL.md

@@ -1,20 +1,16 @@
 ---
 name: nsauditor-ai
 description: >
-  Use this skill whenever the user wants to perform network security scanning, auditing,
-  vulnerability assessment, or host reconnaissance using NSAuditor AI. Triggers include:
-  any mention of 'scan', 'audit', 'vulnerability', 'CVE', 'network security', 'port scan',
-  'service detection', 'OS fingerprinting', 'security assessment', 'penetration test',
-  'probe', 'MITRE ATT&CK', 'CPE', 'NVD', 'TLS audit', 'cipher check', 'banner grab',
-  'SNMP', 'NetBIOS', 'SMB', 'DNS security', 'DKIM', 'SPF', 'DMARC', 'DNSSEC',
-  'certificate audit', 'SARIF', 'CTEM', 'continuous monitoring', 'host discovery',
-  'mDNS', 'UPnP', 'SSDP', 'ARP scan', 'subnet scan', or references to NSAuditor,
-  nsauditor-ai, or the nsauditor MCP server. Also triggers when the user asks to check
-  if a host is up, enumerate services, detect TLS versions, find open ports, look up
-  CVEs for a software version, audit DNS records, check certificate expiry, or perform
-  continuous security monitoring. Use this skill even if the user doesn't explicitly say
-  "NSAuditor" — if they want network security scanning and the nsauditor-ai MCP tools
-  are available, this is the skill to use. Do NOT use for general coding tasks, web
+  Use this skill whenever the user wants network security scanning, auditing, vulnerability
+  assessment, host reconnaissance, or cloud-account security/compliance auditing with NSAuditor
+  AI (via the nsauditor-ai MCP server: scan_host, scan_cloud, probe_service, get_vulnerabilities,
+  list_plugins). Triggers include 'scan', 'audit', 'vulnerability', 'CVE', 'network security',
+  'port scan', 'service detection', 'OS fingerprinting', 'penetration test', 'TLS/cipher audit',
+  'certificate check', 'DNS security', 'SPF/DKIM/DMARC/DNSSEC', 'SNMP/SMB/NetBIOS', 'CTEM',
+  'continuous monitoring', or 'audit my AWS/GCP/Azure account' / 'cloud compliance'. Also use it
+  when the user asks to check if a host is up, enumerate services, find open ports, look up CVEs
+  for a version, audit DNS records, or audit a cloud account — even if they don't say NSAuditor,
+  as long as the nsauditor-ai MCP tools are available. Do NOT use for general coding, web
   development, or non-security topics.
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "nsauditor-ai-agent-skill",
-  "version": "0.1.60",
+  "version": "0.1.62",
   "description": "AI Agent Skill for NSAuditor AI — gives any AI coding agent built-in knowledge of NSAuditor's MCP tools, schemas, plugins, and security audit workflows.",
   "keywords": [
     "nsauditor",