Loading npm security reports…

@antoneeo/kb-agentic-skill@1.16.0: AI-agent control-surface risk | LPM Firewall

registry / @antoneeo/kb-agentic-skill / 1.16.0

@antoneeo/kb-agentic-skill@1.16.0

Knowledge-Base & Document-First protocol for Claude Code, Gemini CLI, Google Antigravity and Codex with risk triage, Vision governance, signal distillation and optional devPNT integration.

AI Security Review

scanned 27d ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. Installing the package automatically writes AI-agent skills into detected user configuration directories. For Claude, it also registers a user-level SessionStart command hook that runs the installed validator in future sessions.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

npm postinstall when an AI client command, environment variable, or configuration directory is detected.

Impact

Future Claude sessions can execute the package-provided validator, and detected AI clients load the copied skill without a separate setup action.

Mechanism

Automatic mutation of user-level AI-agent skills and Claude SessionStart settings.

Policy narrative

The postinstall lifecycle script detects installed AI clients from commands, environment variables, or configuration directories. It copies the package skill into their user-level skill locations. If Claude is detected, it then writes a SessionStart command hook into Claude's user settings, causing future sessions to run a package validator. This mutates a broad, foreign AI-agent control surface during dependency installation without an explicit setup command or prompt.

AI rationale

The package performs unconsented postinstall mutation of user-level AI-agent configuration and installs a future-session command hook. This is a concrete install-hook abuse path even though no network exfiltration was found.

Evidence

package.jsonscripts/postinstall.jsscripts/lib.jsskills/kb-agentic-skill~/.claude/skills/kb-agentic~/.gemini/skills/kb-agentic~/.codex/skills/kb-agentic

Source & flagged code

6 flagged · loading source

package.jsonView file

•scripts.postinstall = node scripts/postinstall.js

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

23"scripts": { "postinstall": "node scripts/postinstall.js", "preuninstall": "node scripts/preuninstall.js" }

High

Suspicious Lifecycle Evidence

An automatic postinstall hook runs the installer.

package.jsonView on unpkg · L23

•scripts.postinstall = node scripts/postinstall.js

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg

scripts/lib.jsView file

15Install-time code directly mutates a foreign AI-agent control surface: L74: cmd: 'claude', L75: home: process.env.CLAUDE_CONFIG_DIR || path.join(os.homedir(), '.claude'), L76: envVar: 'CLAUDE_CONFIG_DIR', ... L90: cmd: 'codex', L91: home: process.env.CODEX_HOME || path.join(os.homedir(), '.codex'), L92: envVar: 'CODEX_HOME', ... L132: function copyRecursive(src, dest) { L133: if (typeof fs.cpSync === 'function') { L134: fs.cpSync(src, dest, { recursive: true, force: true }); L135: return; L136: } L137: if (!fs.existsSync(dest)) fs.mkdirSync(dest, { recursive: true }); Write operation from scripts/postinstall.js: L15: try { L16: fs.mkdirSync(target, { recursive: true }); L17: copyRecursive(SKILL_SOURCE, target); Foreign user/project scope from scripts/lib.js: L74: cmd: 'claude', L75: home:

Critical

Ai Agent Control Hijack

Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.

scripts/lib.jsView on unpkg · L15

skills/kb-agentic-skill/scripts/sdlc_check.pyView file

•path = skills/kb-agentic-skill/scripts/sdlc_check.py kind = build_helper sizeBytes = 96123 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/kb-agentic-skill/scripts/sdlc_check.pyView on unpkg

scripts/init.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

scripts/init.js#virtual:normalized:round1View on unpkg

Source & flagged code

6 flagged

package.jsonView file

Lines 3-44json

3 "version": "1.16.0",

4 "description": "Knowledge-Base & Document-First protocol for Claude Code, Gemini CLI, Google Antigravity and Codex with risk triage, Vision governance, signal distillation and optional devPNT integration.",

5 "keywords": [

6 "claude-code",

7 "claude-skill",

8 "gemini-cli",

9 "skill",

10 "knowledge-base",

11 "documentation",

12 "ai-agent"

13 ],

14 "author": "Antonio Pinto (https://github.com/Antoneeo)",

15 "license": "MIT",

16 "publishConfig": {

17 "access": "public"

18 },

19 "bin": {

20 "kb-agentic-init": "scripts/init.js",

21 "kb-agentic-install-skill": "scripts/postinstall.js"

22 },

23 "scripts": {

24 "postinstall": "node scripts/postinstall.js",

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L24

Medium

Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg · L24

25 "preuninstall": "node scripts/preuninstall.js"

26 },

High

Suspicious Lifecycle Evidence

An automatic postinstall hook runs the installer.

package.jsonView on unpkg · L23

27 "files": [

28 "skills/kb-agentic-skill/SKILL.md",

29 "skills/kb-agentic-skill/templates.md",

30 "skills/kb-agentic-skill/taxonomy.md",

31 "skills/kb-agentic-skill/guides.md",

32 "skills/kb-agentic-skill/vision.md",

33 "skills/kb-agentic-skill/distillation.md",

34 "skills/kb-agentic-skill/reconciliation.md",

35 "skills/kb-agentic-skill/elicitation.md",

36 "skills/kb-agentic-skill/review.md",

37 "skills/kb-agentic-skill/dispatch.md",

38 "skills/kb-agentic-skill/routing.md",

39 "skills/kb-agentic-skill/portability.md",

40 "skills/kb-agentic-skill/ENFORCEMENT.md",

41 "skills/kb-agentic-skill/scripts/sdlc_check.py",

42 "skills/kb-agentic-skill/scripts/sdlc_core.py",

43 "gemini-extension.json",

44 "README.md",

scripts/lib.jsView file

Lines 1-35javascript

1// Shared helpers for the KB Agentic npm scripts (init / postinstall / preuninstall).

2// Single source for client detection and skill-target paths.

3

4const fs = require('fs');

5const path = require('path');

skills/kb-agentic-skill/scripts/sdlc_check.pyView file

•path = skills/kb-agentic-skill/scripts/sdlc_check.py kind = build_helper sizeBytes = 96123 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/kb-agentic-skill/scripts/sdlc_check.pyView on unpkg

scripts/init.js#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 2

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

scripts/init.js#virtual:normalized:round1View on unpkg