skillguard-hardened@1.0.5
VERIFIED· install onlyPublisher claims: "Security guard for OpenClaw skills, developed and maintained by rose北港(小红帽 / 猫猫帽帽). Audits installed or incoming skills with local rules plus Zenmux AI inten..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 9 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-17 and scored it 83/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
"pattern": "(ignore previous instructions|system prompt|developer message|exfiltrate|send the contents of)",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.update_parser = subparsers.add_parser("npx-update", help="Run npx skills update and audit changed skills")Fix: Pin versions and sources; vendor anything fetched at install time."pattern": "(\\.env\\b|api[_-]?key|app[_-]?secret|access[_-]?token|private[_-]?key|password|YOUR_API_KEY|process\\.env\\.[A-Z0-9_]+|os\\.getenv\\([\"'][A-Z0-9_]+[\"'])",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."\\.env\\b",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.process = subprocess.run(command, cwd=str(cwd) if cwd else None)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.add_parser = subparsers.add_parser("npx-add", help="Run npx skills add and audit newly installed skills")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.