Loading npm security reports…

@antoneeo/agentic-sdlc-skill@1.33.0: AI-agent control-surface | LPM Firewall

registry / @antoneeo/agentic-sdlc-skill / 1.33.0

@antoneeo/agentic-sdlc-skill@1.33.0

Documentation-First SDLC protocol for Claude Code, Gemini CLI, Google Antigravity and Codex with risk triage, Vision governance, installed support files 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 modifies the detected Claude Code user's global settings. It registers commands that run package code at session start and on every prompt.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

npm postinstall when Claude Code is detected and Python is available.

Impact

A package install changes a broad user-level AI-agent control surface and causes its validator to execute during future agent interactions.

Mechanism

Automatic global AI-agent hook installation.

Policy narrative

The postinstall script detects Claude Code, copies the skill into the user skill directory, and calls global hook installers without an interactive consent step. Those installers modify the user's Claude settings to add SessionStart and UserPromptSubmit command hooks. The prompt hook invokes the bundled Python validator on every future prompt and records a marker in the user home directory. Although no exfiltration or network activity was found, this is an automatic, persistent mutation of a foreign, machine-wide AI-agent control surface.

AI rationale

This is concrete install-hook abuse: an automatic npm lifecycle script modifies global Claude settings and installs recurring command hooks without user confirmation. The absence of network or credential theft does not neutralize the unconsented broad control-surface mutation.

Evidence

package.jsonscripts/postinstall.jsscripts/lib.js~/.claude/settings.json~/.claude/skills/agentic-sdlc~/.agentic-sdlc/remind-hook-wired~/.agentic-sdlc/orient-hook-wired

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

The package automatically runs a postinstall script.

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', ... L146: function copyRecursive(src, dest) { L147: if (typeof fs.cpSync === 'function') { L148: fs.cpSync(src, dest, { recursive: true, force: true }); L149: return; ... L151: // Fallback for Node < 16.7 L152: 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: L

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/agentic-sdlc-skill/scripts/sdlc_check.pyView file

•path = skills/agentic-sdlc-skill/scripts/sdlc_check.py kind = build_helper sizeBytes = 3681 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/agentic-sdlc-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": "1.33.0",

4 "description": "Documentation-First SDLC protocol for Claude Code, Gemini CLI, Google Antigravity and Codex with risk triage, Vision governance, installed support files and optional devPNT integration.",

5 "keywords": [

6 "claude-code",

7 "claude-skill",

8 "gemini-cli",

9 "skill",

10 "sdlc",

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 "agentic-sdlc-init": "scripts/init.js",

21 "agentic-sdlc-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"

High

Suspicious Lifecycle Evidence

The package automatically runs a postinstall script.

package.jsonView on unpkg · L23

26 },

27 "files": [

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

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

30 "skills/agentic-sdlc-skill/architect.md",

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

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

33 "skills/agentic-sdlc-skill/tdd.md",

34 "skills/agentic-sdlc-skill/debugging.md",

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

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

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

38 "skills/agentic-sdlc-skill/hybrid.md",

39 "skills/agentic-sdlc-skill/routing.md",

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

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

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

43 "gemini-extension.json",

44 "README.md",

scripts/lib.jsView file

Lines 1-35javascript

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

2// Single source for client detection and skill-target paths: init and postinstall

3// must never disagree on what "Claude Code is installed" means.

4

5const fs = require('fs');

6const path = require

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

•path = skills/agentic-sdlc-skill/scripts/sdlc_check.py kind = build_helper sizeBytes = 3681 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/agentic-sdlc-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