eval-skills@0.1.1
CAUTION· static onlyPublisher claims: "AI Agent Skill unit testing framework. A framework-agnostic toolkit for discovering, scaffolding, selecting, evaluating, and reporting on AI skills. Use this..." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-21 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
"python3 `cat /etc/passwd`",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// python3 -c "import time; time.sleep(60)" 会被 500ms 后 killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// Yes, printTable uses console.log directly for json output.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."python3; rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.it("should enforce hard timeout and kill process", async () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.it("should kill container when hard timeout exceeded", async () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// 当前架构 execute() 内部负责了生命周期管理 (ProcessSandbox kill tree, DockerSandbox rm container)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."python3; rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.["shell 管道注入", "python3 skill.py; rm -rf /"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."python3 ../../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.mockChild.kill = vi.fn();Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.entrypoint: "npx -y @modelcontextprotocol/server-filesystem /path/to/allowed/dir",Fix: Pin versions and sources; vendor anything fetched at install time.["sudo 提权", "sudo python3 skill.py"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.["shell 管道注入", "python3 skill.py; rm -rf /"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.["重定向注入", "python3 skill.py > /etc/passwd"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.["路径遍历", "python3 ../../etc/passwd"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.sensitive_files = ["/etc/passwd", "/etc/shadow", "/root/.ssh/id_rsa", "/proc/1/environ"]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.["AND 链注入", "python3 skill.py && cat /etc/shadow"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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
15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim islinxu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- Destructive command against a filesystem root or device≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.