li-vibe-codebase-audit@2.0.1
CAUTION· install onlyPublisher claims: "Comprehensive automated and multi-model AI security audits for AI-generated codebases, checking vulnerabilities, secrets, dependency risks, and config issues." 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 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
1. Install Ollama: curl -fsSL https://ollama.com/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.if '.env.example' not in str(env_file):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.- Exposed .env file detectionFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.1. Install Ollama: curl -fsSL https://ollama.com/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# Rule 2: Check for hardcoded IPsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."Exposed .env files",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Rule 1: Prevent usage of dangerous functionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.for env_file in project_path.rglob('.env*'):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Rule 3: Check for debug printsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# Rule 4: SQL injection patternsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# Check for exposed .env filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return {"error": "OPENROUTER_API_KEY not set. Set environment variable or pass api_key parameter."}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'*.pyc', 'venv', '.venv', 'dist', 'build', '.env'}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Rule 5: Weak random number generationFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."""Check for exposed .env files"""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
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim 43622283: 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.
- Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.