Loading npm security reports…

@ai-content-space/loopx@0.8.4: AI-agent control-surface risk | LPM Firewall

registry / @ai-content-space/loopx / 0.8.4

@ai-content-space/loopx@0.8.4

Docs-first engineering discipline for agentic coding assistants

AI Security Review

scanned 7d ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. npm postinstall mutates broad Codex and Claude instruction files and installs skills into user agent directories. The mutation occurs without an explicit setup command or consent prompt.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

npm installation, unless LOOPX_SKIP_POSTINSTALL=1 or LOOPX_POSTINSTALL=0 is set beforehand.

Impact

Changes default AI-agent behavior across the user's Codex and Claude environments.

Mechanism

postinstall copies skills and appends managed agent-routing blocks

Policy narrative

Installing the package automatically invokes scripts/install-skills.mjs. Its default target set is Codex and Claude; installation copies bundled skills into user-level agent directories and then calls installAgentGuidance. That function always upserts a loopx routing block into ~/.codex/AGENTS.md and ~/.claude/CLAUDE.md, broad instruction/control surfaces for other agent sessions. The optional CLI prompt only governs additional context guidance, not this postinstall routing mutation.

Rationale

The package performs unconsented postinstall mutation of foreign, broad AI-agent control surfaces. This meets the blocking policy despite no observed data exfiltration or remote payload execution.

Evidence

package.jsonscripts/install-skills.mjssrc/install-discovery.mjstemplates/working-agreement.md~/.agents/skills/*~/.agents/.skill-lock.json~/.claude/skills/*~/.claude/CLAUDE.md~/.codex/AGENTS.md

Source & flagged code

4 flagged · loading source

package.jsonView file

•scripts.postinstall = node scripts/install-skills.mjs

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg

src/install-discovery.mjsView file

78Install-time AI-agent control hijack evidence: L78: kind: 'plugin', L79: sourceRelativePath: 'plugins/loopx/.codex-plugin/plugin.json', L80: }, ... L106: const home = resolve(env.LOOPX_HOME || env.HOME || process.cwd()); L107: return resolve(env.LOOPX_AGENTS_ROOT || join(home, '.agents')); L108: } ... L115: const home = resolve(env.LOOPX_HOME || env.HOME || process.cwd()); L116: return resolve(env.LOOPX_CLAUDE_SKILLS_ROOT || join(home, '.claude', 'skills')); L117: } ... L120: const home = resolve(env.LOOPX_HOME || env.HOME || process.cwd()); L121: return resolve(env.LOOPX_CLAUDE_SETTINGS_PATH || join(home, '.claude', 'settings.json')); L122: } Payload evidence from [redacted]-features.md: L186: } L187: return ctx.JSON(200, resp) L188: }) ... L295: "kratos-mcp": { L296: "url": "http://local

Critical

Ai Agent Control Hijack

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

src/install-discovery.mjsView on unpkg · L78

93function jsonClone(value) { L94: return JSON.parse(JSON.stringify(value)); L95: } ... L100: L101: export function getProjectRoot(env = process.env) { L102: return resolve(env.LOOPX_PROJECT_ROOT || PROJECT_ROOT); ... L105: export function getAgentsRoot(env = process.env) { L106: const home = resolve(env.LOOPX_HOME || env.HOME || process.cwd()); L107: return resolve(env.LOOPX_AGENTS_ROOT || join(home, '.agents')); ... L244: path, L245: data: { L246: version: 3,

Low

Weak Crypto

Package source references weak cryptographic algorithms.

src/install-discovery.mjsView on unpkg · L93

skills/code-darwin/scripts/audit_codebase.pyView file

•path = skills/code-darwin/scripts/audit_codebase.py kind = build_helper sizeBytes = 21610 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/code-darwin/scripts/audit_codebase.pyView on unpkg

Source & flagged code

4 flagged

package.jsonView file

Lines 59-93json

59 "skills/plan2exec/",

60 "skills/plan-reviewer/",

61 "skills/refactor-plan/",

62 "skills/requirement-analyzer/",

63 "skills/sql-style/",

64 "skills/spec/",

65 "skills/tdd/",

66 "skills/using-git-worktrees/",

67 "skills/verify/",

68 "templates/spec.md",

69 "templates/working-agreement.md",

70 "templates/intake-clarification.md",

71 "templates/intake-requirements.md",

72 "plugins/loopx/",

73 "!plugins/loopx/scripts/plugin-install.test.mjs"

74 ],

75 "publishConfig": {

76 "access": "public"

77 },

78 "scripts": {

79 "postinstall": "node scripts/install-skills.mjs",

High

Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg · L79

80 "eval:agent": "node scripts/run-agent-evals.mjs",

81 "eval:codex-normalize": "node scripts/normalize-codex-agent-trace.mjs",

82 "eval:codex-live": "node scripts/run-codex-live-agent-evals.mjs",

83 "eval:claude-live": "node scripts/run-claude-live-agent-evals.mjs",

84 "eval:darwin-simple": "node scripts/run-darwin-simple-evals.mjs",

85 "eval:req-demo": "node scripts/run-req-demo-evals.mjs",

86 "eval:benchmark": "node scripts/run-benchmark-evals.mjs",

87 "eval:benchmark:aggregate": "node scripts/aggregate-benchmark-reports.mjs",

88 "eval:drills": "node scripts/run-drills.mjs",

89 "eval:aggregate": "node scripts/aggregate-agent-evals.mjs",

90 "test": "node scripts/verify-skills.mjs && node --test test/*.test.mjs"

91 }

92}

93

src/install-discovery.mjsView file

Lines 58-113javascript

58const LOOPX_AGENT_GUIDANCE_HEADING = '## loopx Specs And Memory';

59const LOOPX_AGENT_GUIDANCE_CONTENT = [

60 LOOPX_AGENT_GUIDANCE_HEADING,

61 '',

62 'When working in a repository that uses loopx:'

skills/code-darwin/scripts/audit_codebase.pyView file

•path = skills/code-darwin/scripts/audit_codebase.py kind = build_helper sizeBytes = 21610 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/code-darwin/scripts/audit_codebase.pyView on unpkg