lighthouse-audit
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill documentation instructs the user to install the 'lighthouse' CLI via npm and several Python libraries (click, pandas, jinja2). While these are reputable tools, they constitute external dependency surfaces.
- PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it retrieves and processes content from arbitrary external URLs. 1. Ingestion points: External website URLs provided for auditing. 2. Boundary markers: No delimiters or ignore-instructions warnings are present in the provided instructions. 3. Capability inventory: The skill performs subprocess calls to the Lighthouse CLI and writes report files to the local system. 4. Sanitization: No sanitization of the audited content is visible in the provided metadata.
- NO_CODE (SAFE): The file 'scripts/main.py', which contains the actual execution logic, is missing from the provided skill files. This prevents a thorough audit of the command-line construction and data handling.
Audit Metadata