auto-hook@1.0.0
VERIFIED· install onlyPublisher claims: "检查指定 SKILL 是否存在偷懒、跳步、简化执行等问题,并确保该 SKILL 末尾附有自审计钩子(autohook); 也可撤销已注入的钩子,将 SKILL 恢复原样。 支持 Claude Code、OpenAI Codex CLI、OpenClaw 三大智能体,自动适配 Linux / macOS / Win..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-20 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
npx skills find "react testing"Fix: Pin versions and sources; vendor anything fetched at install time.npx skills updateFix: Pin versions and sources; vendor anything fetched at install time.npx skills add vercel-labs/agent-skills -a claude-code -a codexFix: Pin versions and sources; vendor anything fetched at install time.npx skills add vercel-labs/agent-skillsFix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.