agentmods.dev

dependency-audit

A safety check for npm packages, JavaScript or TypeScript repositories, dependency updates, and lockfiles. It looks for malware and risky installation scripts that could run before or during package use.

In plain words
What is it for?
Use it to review outdated packages, project dependencies, npm lockfiles, GitHub repositories, and packages before they are added to a JavaScript or TypeScript project.
Why use it?
It helps reduce supply-chain risk before installing, building, testing, importing, or running unfamiliar dependencies. It requires choosing whether to inspect the tool's own dependencies, the current project's dependencies, or both.

Skill for Claude CodeCodex

2 1mo ago C scan 45 tokens original MIT
View the source file testzugang/pi-plugins
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/testzugang/pi-plugins/dependency-audit
Any agent
npx skills add testzugang/pi-plugins --skill dependency-audit
Clone the repo
git clone --depth 1 https://github.com/testzugang/pi-plugins

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,689 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 4 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.05689
Opus 5 $0.00023 $0.02844
Sonnet 5 $0.00009 $0.01138
Haiku 4.5 $0.00005 $0.00569

Measured 2d ago against content hash 7a29540dee1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

dependency-audit scanned grade C with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/npm_ts_static_triage.py, scripts/pi-check-all-updates.sh, scripts/pi-check-current-global-versions.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

6. **Credential Harvesting**: Code sucht nach `GITHUB_TOKEN`, `NPM_TOKEN`, AWS-/Vault-/GitHub-Actions-OIDC-Secrets oder lokalen Dateien wie `.npmrc`, `.aws/credentials`, `.config/gh/hosts.yml`.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

- Cloud-/Vault-Probes: `169.254.169.254`, `metadata.google.internal`, `127.0.0.1:8200`.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fL -o package-under-review.tgz '<dist.tarball-url>'

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Script-Inhalte mit `curl`, `wget`, `fetch`, `axios`, `got`, `node -e`, `eval`, `new Function`, `child_process`, `execSync`, `spawn`, `bun`, `python`, `bash`, `powershell`, `chmod +x`, Base64-/zlib-/AES-Decodern.
packages/pi-dependency-audit/skills/dependency-audit/SKILL.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

npm/TypeScript Package & Dependency Audit Skill

Ziel

Nutze diesen Skill, wenn TypeScript-/JavaScript-Code, ein npm-Paket, ein GitHub-Repository, ein Dependency-Update oder ein npm-Lockfile vor der Nutzung geprüft werden soll. Der Fokus liegt auf Malware- und Supply-Chain-Erkennung vor npm install, npm ci, Build, Test, Import oder IDE-/CI-Ausführung.

Automatischer Workflow (ohne Parameter)

Wenn der Skill ohne weitere Parameter aufgerufen wird (z.B. /skill:dependency-audit), muss immer zuerst eine explizite Modus-Auswahl über user_select erfolgen.

Pflichtfrage (immer, als erster Schritt):

  • "Pi-Dependencies prüfen"
  • "Projekt-Dependencies (aktuelles Verzeichnis) prüfen"
  • "Beides prüfen"

Regeln:

  1. Diese Auswahl darf nicht übersprungen werden, auch nicht bei fehlender package.json.
  2. Existiert bei Auswahl "Projekt-Dependencies" keine package.json, gib eine klare Rückfrage: Pfad angeben oder auf Pi-Dependencies wechseln.
  3. Starte keine Prüfung, bevor der Nutzer einen der drei Modi bestätigt hat.

Führe dann je nach Auswahl die entsprechenden Szenarien aus:

Szenario A: Lokale npm-Abhängigkeiten

  1. Führe npm outdated --json (oder ein äquivalentes Tool) aus, um die Liste verfügbarer Updates zu ermitteln.
  2. Iteriere durch die ermittelten Pakete.
  3. Führe für jedes Paket die in diesem Skill beschriebenen statischen Prüfungen durch.
  4. Generiere einen aggregierten JSON-Report und einen Markdown-Report mit Detailabschnitten für abgelehnte/blockierte Updates.

Szenario B: Globale Pi-Erweiterungen

  1. Nutze bevorzugt die mitgelieferten Hilfsskripte statt ad-hoc Bash-Loops:
    • scripts/pi-check-current-global-versions.sh
    • scripts/pi-check-latest-npm-versions.sh
    • scripts/pi-check-git-source-updates.sh
    • optional End-to-End: scripts/run_pi_dependency_audit.py
  2. Nutze die Config-Resolution für Sicherheitsrichtlinien (Priorität):
    • --config /path/to/config.json
    • ~/.pi/dependency-audit.json
    • skills/dependency-audit/config.json
    • Fallback auf Defaults
  3. min_update_age_hours steuert die Mindest-Altersschwelle für Updates. Default ist 24.
  4. trusted_peer_dependency_scopes und trusted_peer_dependency_packages steuern enge Allowlists für Peer-Dependency-Versionranges. Default: @earendil-works/* ist als Peer-Dependency-Scope vertrauenswürdig; diese Regel gilt nur für peerDependencies, nicht für dependencies, devDependencies, optionalDependencies, overrides oder resolutions.
  5. Ermittle für jedes Paket, ob auf der Remote-Quelle (z. B. auf GitHub) neue Commits oder Versionen verfügbar sind.
  6. Wenn ein Update jünger als min_update_age_hours ist, markiere es als too_fresh mit SKIP_TOO_FRESH.
  7. Klone/lade die übrigen Updates temporär herunter, ohne sie zu installieren oder Scripte auszuführen.
  8. Führe die in diesem Skill beschriebenen statischen Prüfungen auf dem neuen Code durch.
  9. Generiere immer einen aggregierten JSON-Report und einen Markdown-Report. Der Markdown-Report muss Detailabschnitte für blockierte/quarantänisierte, fehlerhafte oder per Age-Gate verschobene Updates enthalten, damit abgelehnte Updates nachträglich erkundet werden können.
  10. Generiere einen Report, der angibt, welche Pi-Erweiterungen sicher aktualisiert werden können. Präsentiere am Ende des Berichts immer einen maßgeschneiderten nativen pi update-Vorschlag (siehe Abschnitt "Natives Pi-Paketmanagement (pi update)"), der blockierte/quarantänisierte oder zu frische Pakete explizit auslässt.

Read the full file on GitHub · 385 lines

Files

What ships with it

18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 385 lines · 45 tokens per session scan C 7a29540dee1c

Subscribe to this mod's changes

dependency-audit is a skill published in the GitHub repository testzugang/pi-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 5,689 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 4 findings (reaches for credential files, cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens