Loading npm security reports…

llm-wiki-loop@1.2.0: AI-agent control-surface risk | LPM Firewall

registry / llm-wiki-loop / 1.2.0

llm-wiki-loop@1.2.0

The production framework for self-improving & self-organizing LLM knowledge vaults — grounding invariants, code drift detection, auto-skillification, and 1-click multi-agent setup.

AI Security Review

scanned 2h ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. Installing the package invokes a postinstall script that copies an agent skill into detected cross-vendor agent directories. It also creates a project .agents skill directory when none is present.

Static reason

High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review

Trigger

npm install (postinstall)

Impact

Unconsented modification of AI-agent instruction/control surfaces.

Mechanism

Automatic cross-agent skill deployment

Policy narrative

During npm installation, the lifecycle hook runs scripts/install.js. It recursively copies the bundled wiki-manager skill into detected agent-runtime skill directories; for normal project installs it targets existing runtime directories and otherwise creates .agents/skills. This changes AI-agent behavior without requiring an explicit package command.

Rationale

The package performs unconsented postinstall mutation of foreign and broad AI-agent control surfaces, including a fallback that creates one. This meets the firewall block policy despite no observed exfiltration or network behavior.

Evidence

package.jsonscripts/install.jsskills/wiki-manager/SKILL.mdskills/wiki-manager/~/.claude/skills/wiki-manager~/.config/opencode/skills/wiki-manager~/.agents/skills/wiki-manager<project>/.agents/skills/wiki-manager

Decision evidence

Source & flagged code

6 flagged · loading source

package.jsonView file

•scripts.postinstall = node scripts/install.js

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

32"scripts": { "lint": "node --check bin/cli.js \u0026\u0026 node --check scripts/install.js", "test": "py -m unittest discover -s tests", "test:cli": "node bin/cli.js doctor", "postinstall": "node scripts/install.js" },

High

Suspicious Lifecycle Evidence

package.json runs scripts/install.js automatically as postinstall.

package.jsonView on unpkg · L32

•scripts.postinstall = node scripts/install.js

Medium

Ambiguous Install Lifecycle Script

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

package.jsonView on unpkg

scripts/install.jsView file

5// Global install (npm i -g): copies into the home skill dirs of detected L6: // runtimes (Claude Code ~/.claude/skills, opencode ~/.config/opencode/skills, L7: // Codex CLI ~/.agents/skills). L8: // L9: // Project install (npm i in a project): copies into the project's runtime L10: // skill dirs (.claude/skills, .opencode/skills, .agents/skills, L11: // .cursor/skills) whose base directory already exists, or falls back to L12: // .agents/skills (Open Agent standard). L13: ... L21: const GLOBAL_RUNTIMES = [ L22: { marker: path.join(HOME, ".claude"), dir: path.join(HOME, ".claude", "skills") }, L23: { marker: path.join(HOME, ".config", "opencode"), dir: path.join(HOME, ".config", "opencode", "skills") },

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/install.jsView on unpkg · L5

•matchType = normalized_sha256 matchedPackage = llm-wiki-loop@1.1.1 matchedPath = scripts/install.js matchedIdentity = npm:bGxtLXdpa2ktbG9vcA:1.1.1 similarity = 1.000 summary = normalized source hash matched finalized malicious source

High

Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

scripts/install.jsView on unpkg

skills/wiki-manager/scripts/check_evidence.pyView file

•path = skills/wiki-manager/scripts/check_evidence.py kind = build_helper sizeBytes = 20323 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/wiki-manager/scripts/check_evidence.pyView on unpkg

Source & flagged code

6 flagged

package.jsonView file

Lines 12-46json

12 "self-improving",

13 "claude-code",

14 "codex",

15 "opencode",

16 "obsidian",

17 "skills"

18 ],

19 "bin": {

20 "llm-wiki": "bin/cli.js",

21 "llm-wiki-loop": "bin/cli.js"

22 },

23 "files": [

24 "bin",

25 "skills",

26 "scripts",

27 "README.md",

28 "SPEC.md",

29 "AGENTS.md",

30 "LICENSE"

31 ],

32 "scripts": {

33 "lint": "node --check bin/cli.js \u0026\u0026 node --check scripts/install.js",

34 "test": "py -m unittest discover -s tests",

35 "test:cli": "node bin/cli.js doctor",

36 "postinstall": "node scripts/install.js"

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L36

Medium

Ambiguous Install Lifecycle Script

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

package.jsonView on unpkg · L36

37 },

High

Suspicious Lifecycle Evidence

package.json runs scripts/install.js automatically as postinstall.

package.jsonView on unpkg · L32

38 "engines": {

39 "node": "\u003e=16.17"

40 },

41 "homepage": "https://github.com/PALAN-K/llm-wiki-loop#readme",

42 "repository": {

43 "type": "git",

44 "url": "git+https://github.com/PALAN-K/llm-wiki-loop.git"

45 }

46}

scripts/install.jsView file

Lines 1-25javascript

1#!/usr/bin/env node

2// Installs the wiki-manager skill into detected agent runtimes.

3// Postinstall-safe: never fails an npm install; prints guidance instead.

4//

5// Global install (npm i -g): copies into the home skill dirs of detected

6// runtimes (Claude Code ~/.claude/skills, opencode ~/.config/opencode/skills,

7// Codex CLI ~/.agents/skills).

8//

9// Project install (npm i in a project): copies into the project's runtime

10// skill dirs (.claude/skills, .opencode/skills, .agents/skills,

skills/wiki-manager/scripts/check_evidence.pyView file

•path = skills/wiki-manager/scripts/check_evidence.py kind = build_helper sizeBytes = 20323 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/wiki-manager/scripts/check_evidence.pyView on unpkg