Loading npm security reports…

llm-wiki-loop@1.0.0: AI-agent control-surface risk | LPM Firewall

registry / llm-wiki-loop / 1.0.0

llm-wiki-loop@1.0.0

The reference architecture for LLM-maintained knowledge vaults — schema, lifecycle loop, machine verification, self-installation. Installs the wiki-manager skill into your agent runtime (Claude Code, Codex CLI, opencode).

AI Security Review

scanned 3h ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. npm postinstall automatically installs and forcibly overwrites a skill across detected third-party AI-agent control surfaces. This occurs for global installs and for existing agent directories in the current project.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

npm install or npm install -g

Impact

Unconsented cross-agent prompt/control-surface mutation and persistence until manually removed.

Mechanism

postinstall copies bundled skill into detected runtime skill directories

Policy narrative

Installing the package invokes its postinstall script without a separate setup command. The script detects multiple unrelated AI-agent runtimes and force-copies its bundled wiki-manager skill into each matching global or project skill directory, overwriting an existing skill of that name. This is a broad foreign agent control-surface mutation at install time.

Rationale

The source establishes concrete, automatic, forceful mutation of foreign AI-agent skill directories during npm installation. Under the install-control-surface policy, this requires blocking despite no observed network exfiltration. Product guard normalized a concrete AI-agent control hijack publish_block to the blockable dangerous-capability shape.

Evidence

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

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 && 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

postinstall runs scripts/install.js automatically.

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. ... L20: const GLOBAL_RUNTIMES = [ L21: { marker: path.join(HOME, ".claude"), dir: path.join(HOME, ".claude", "skills") }, L22: { marker: path.join(HOME, ".config", "opencode"), dir: path.join(HOME, ".config", "opencode", "skills") }, L23: { marker: path.join(HOME, ".agents"), dir: path.join(HOME, ".agents", "skills") }, L24: { marker: path.join(HOME, ".cursor"), dir: path.join(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/install.jsView on unpkg · L5

bin/cli.jsView file

•Runtime or CLI code links a write operation to an explicit external AI-agent control path: uld not install to ${base}: ${err.message}`); } } } } } if (installed.length > 0) { console.log(`\nsuccessfully installed wiki-manager skill to:`); for (const dest of installed) { console.log(` - ${dest}`); } console.log(`\nrestart your agent runtime to activate.`); } else { console.log(`no supported agent runtime found. use --global or specify --custom <path>.`); } } function runinit(targetdir) { const root = targetdir ? path.resolve(targetdir) : process.cwd(); console.log(`scaffolding llm-wiki vault in: ${root}\n`); const dirs = [ 'raw/notes', 'raw/data', 'raw/assets', 'wiki/concepts', 'wiki/topics', 'wi

High

External Ai Agent Control Surface Mutation

Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.

bin/cli.jsView on unpkg

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

•path = skills/wiki-manager/scripts/check_evidence.py kind = build_helper sizeBytes = 15598 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 12-47json

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 && 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

postinstall runs scripts/install.js automatically.

package.jsonView on unpkg · L32

38 "engines": {

39 "node": ">=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}

47

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,

bin/cli.jsView file

•Runtime or CLI code links a write operation to an explicit external AI-agent control path: uld not install to ${base}: ${err.message}`); } } } } } if (installed.length > 0) { console.log(`\nsuccessfully installed wiki-manager skill to:`); for (const dest of installed) { console.log(` - ${dest}`); } console.log(`\nrestart your agent runtime to activate.`); } else { console.log(`no supported agent runtime found. use --global or specify --custom <path>.`); } } function runinit(targetdir) { const root = targetdir ? path.resolve(targetdir) : process.cwd(); console.log(`scaffolding llm-wiki vault in: ${root}\n`); const dirs = [ 'raw/notes', 'raw/data', 'raw/assets', 'wiki/concepts', 'wiki/topics', 'wi

High

External Ai Agent Control Surface Mutation

Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.

bin/cli.jsView on unpkg

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

•path = skills/wiki-manager/scripts/check_evidence.py kind = build_helper sizeBytes = 15598 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

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