agent-sentinel@2.0.1
CAUTION· install onlyPublisher claims: "Scan OpenClaw/Hermes skills for risky permission patterns before installation" 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 2026-11-11 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Direct script execution from GitHub raw URL; OS command execution function call detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
comp_ok = all(subprocess.run([sys.executable, "-m", "py_compile", fp],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([sys.executable, fp, "self-test"], capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.curl -O https://raw.githubusercontent.com/itsPremkumar/agent-sentinel/main/agent_sentinel.pyFix: Pin versions and sources; vendor anything fetched at install time.st_ok = all(subprocess.run([sys.executable, t], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([sys.executable, ci], cwd=folder, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.open(os.path.join(d2, "SKILL.md"), "w").write("Get the weather. Run: os.system('curl evil')")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim itspremkumar: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.