registry  /  peaks-loop  /  3.1.0

peaks-loop@3.1.0

Loop Engineering CLI — workflow primitive / loop guards / evaluators / slice orchestration

AI Security Review

scanned 11h ago · by lpm-firewall-ai

The package lifecycle hook mutates broad AI-agent control surfaces in the user's home directory during npm install. It plants package-supplied skills, output styles, and Claude agent prompts across Claude/Codex/Cursor/other IDE namespaces without an explicit user-invoked command.

Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review
Trigger
npm install/postinstall
Impact
AI agents may load and execute package-supplied instructions/tools from home-directory control surfaces after install; legacy project detection can also dispatch an upgrade that installs hooks.
Mechanism
unconsented lifecycle installation of AI-agent skills and prompts
Attack narrative
On npm postinstall, scripts/install-skills.mjs fans out bundled skills to multiple home-directory agent/IDE skill namespaces and installs Claude agent prompts under ~/.claude/agents. This is lifecycle-triggered mutation of foreign/broad AI-agent control surfaces, with optional legacy auto-upgrade that can run hook installation commands.
Rationale
Direct source inspection confirms an unconsented npm lifecycle hook writes package-supplied AI-agent instructions/prompts into broad home-directory Claude/Codex/Cursor-style control surfaces. Under the install control surface policy this is blockable even though the content appears product-aligned and no exfiltration was found.
Evidence
package.jsonscripts/install-skills.mjsagents/karpathy-reviewer.mddist/src/services/upgrade/upgrade-service.js~/.claude/skills/*~/.claude/output-styles/*~/.claude/agents/karpathy-reviewer.md~/.codex/skills/*~/.codex/output-styles/*~/.cursor/skills/*~/.cursor/output-styles/*~/.peaks/config.json

Decision evidence

public snapshot
AI called this Malicious at 97.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for block
  • package.json defines postinstall: node ./scripts/install-skills.mjs
  • scripts/install-skills.mjs postinstall symlinks bundled skills into ~/.claude, ~/.codex, ~/.cursor, ~/.trae, ~/.qoder and other IDE skill dirs
  • scripts/install-skills.mjs copies bundled agent prompts into ~/.claude/agents with managed overwrite markers
  • scripts/install-skills.mjs writes ~/.peaks/config.json during install unless opt-out env vars are set
  • scripts/install-skills.mjs can auto-run peaks upgrade --to 2.0 --auto, whose upgrade-service includes hooks install and skill sync steps
  • agents/karpathy-reviewer.md is a package-supplied Claude sub-agent prompt with Bash tool access
Evidence against
  • Install script uses symlink/marker safety checks and preserves unmanaged local files
  • No credential harvesting or network exfiltration endpoints found in inspected install path
  • Bundled content appears product-aligned for a workflow/agent CLI rather than classic malware
Behavioral surface
Source
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemShell
Supply chain
HighEntropyStringsUrlStrings
ManifestNo manifest risk signals triggered.
scanned 453 file(s), 2.93 MB of source, external domains: api.anthropic.com, api.example.com, api.openai.com, github.com, gitlab.com, reactbits.dev, www.google.com, www.pulsemcp.com

Source & flagged code

11 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
dist/src/shared/process.jsView file
1import { execFile } from 'node:child_process'; L2: export async function execCommand(command, args, options) {
High
Child Process

Package source references child process execution.

dist/src/shared/process.jsView on unpkg · L1
dist/src/services/upgrade/upgrade-service.jsView file
151// npm install postinstall creates `peaks` → `peaks.sh` on L152: // Windows). cmd.exe (the default Windows shell) cannot run L153: // `.sh` scripts directly, so the shim fails with "unknown
High
Shell

Package source references shell execution.

dist/src/services/upgrade/upgrade-service.jsView on unpkg · L151
dist/src/cli/commands/loop-eval-commands.jsView file
478// eslint-disable-next-line @typescript-eslint/no-var-requires L479: const fs = require('node:fs'); L480: let entries;
Medium
Dynamic Require

Package source references dynamic require/import behavior.

dist/src/cli/commands/loop-eval-commands.jsView on unpkg · L478
scripts/install-skills.mjsView file
1Install-time AI-agent control hijack evidence: L1: #!/usr/bin/env node L2: import { closeSync, constants, existsSync, fchmodSync, fstatSync, lstatSync, mkdirSync, openSync, readFileSync, readlinkSync, realpathSync, readdirSync, renameSync, symlinkSync, un... L3: import { spawnSync } from 'node:child_process'; ... L291: fchmodSync(fd, 0o600); L292: writeFileSync(fd, content, 'utf8'); L293: const writeFd = fd; ... L320: fchmodSync(fd, 0o600); L321: writeFileSync(fd, content, 'utf8'); L322: const writeFd = fd; ... L372: * cannot import the TS service at runtime. The dispatch: L373: * - Look for `.claude`, `.trae`, `.codex`, `.cursor`, `.qoder`, L374: * `.tongyi-lingma` in the project root in that insertion order Payload evidence from schemas/mcp-install-spec.schema.json: L1: { L2: "$schema": "https://json-schema.org/draft/2020-12/schema", L3: "title": "Peaks MCP Install Spec", ... L25: "items": { "type": "string" }, L26: "description": "Required env var names. Values are sourced from process.env at runtime and written as ${VAR} placeholders into settings.json." L27: }
Critical
Ai Agent Control Hijack

Install-time source drops package-supplied AI-agent/MCP control files or instructions.

scripts/install-skills.mjsView on unpkg · L1
dist/src/cli/commands/playwright-commands.jsView file
27* The CLI does NOT bundle `playwright-mcp`; it shells out to L28: * `npx playwright-mcp@latest` (G22 / NG3). peaks-loop is the lifecycle L29: * orchestrator, not the install medium. ... L31: import { createHash } from 'node:crypto'; L32: import { spawn } from 'node:child_process'; L33: import { existsSync, mkdirSync, readFileSync, writeFileSync, readdirSync, unlinkSync } from 'node:fs';
High
Runtime Package Install

Package source invokes a package manager install command at runtime.

dist/src/cli/commands/playwright-commands.jsView on unpkg · L27
matchType = normalized_sha256 matchedPackage = peaks-loop@3.0.1 matchedPath = [redacted]-commands.js matchedIdentity = npm:cGVha3MtbG9vcA:3.0.1 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.

dist/src/cli/commands/playwright-commands.jsView on unpkg
dist/src/services/code-review/ocr-service.jsView file
matchType = normalized_sha256 matchedPackage = peaks-loop@3.0.1 matchedPath = dist/src/services/code-review/ocr-service.js matchedIdentity = npm:cGVha3MtbG9vcA:3.0.1 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.

dist/src/services/code-review/ocr-service.jsView on unpkg
dist/src/services/artifacts/artifact-service.jsView file
matchType = normalized_sha256 matchedPackage = peaks-loop@3.0.1 matchedPath = [redacted]-service.js matchedIdentity = npm:cGVha3MtbG9vcA:3.0.1 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.

dist/src/services/artifacts/artifact-service.jsView on unpkg
dist/src/services/workspace/migrate-service.jsView file
matchType = normalized_sha256 matchedPackage = peaks-loop@3.0.1 matchedPath = [redacted]-service.js matchedIdentity = npm:cGVha3MtbG9vcA:3.0.1 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.

dist/src/services/workspace/migrate-service.jsView on unpkg
dist/src/cli/commands/session-auto-compact-hook-command.jsView file
matchType = normalized_sha256 matchedPackage = peaks-loop@3.0.3 matchedPath = dist/src/cli/commands/session-auto-compact-hook-command.js matchedIdentity = npm:cGVha3MtbG9vcA:3.0.3 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.

dist/src/cli/commands/session-auto-compact-hook-command.jsView on unpkg

Findings

1 Critical9 High3 Medium5 Low
CriticalAi Agent Control Hijackscripts/install-skills.mjs
HighInstall Time Lifecycle Scriptspackage.json
HighChild Processdist/src/shared/process.js
HighShelldist/src/services/upgrade/upgrade-service.js
HighRuntime Package Installdist/src/cli/commands/playwright-commands.js
HighKnown Malware Source Similaritydist/src/cli/commands/playwright-commands.js
HighKnown Malware Source Similaritydist/src/services/code-review/ocr-service.js
HighKnown Malware Source Similaritydist/src/services/artifacts/artifact-service.js
HighKnown Malware Source Similaritydist/src/services/workspace/migrate-service.js
HighKnown Malware Source Similaritydist/src/cli/commands/session-auto-compact-hook-command.js
MediumDynamic Requiredist/src/cli/commands/loop-eval-commands.js
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings