skill-security-scan@1.0.0
CAUTION· install onlyPublisher claims: "Skill安全扫描工具。L1自动化扫描(scanner.py)+ L2人工审查协议(红旗清单+风险分级)。发现风险时推送信息交给人工复核。" 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 2026-11-10 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
✗ 读取 ~/.ssh, ~/.aws, ~/.config 而无明确理由Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.AUTO_UPDATE_INTERVAL = 1 * 24 * 3600 # 1 day (seconds)Fix: Pin versions and sources; vendor anything fetched at install time.# Check for auto-update on every run (once every 7 days)Fix: Pin versions and sources; vendor anything fetched at install time.| 远程安装(clawhub/npx skills add) | 安装完成后立即扫描 |Fix: Pin versions and sources; vendor anything fetched at install time.✗ 请求提升/sudo 权限Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.log(f" ⚠️ Auto-update check failed: {e} (normal operation unaffected)")Fix: 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.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim paudyyin: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.