performance-profiling
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The script scripts/lighthouse_audit.py uses subprocess.run to execute the lighthouse CLI. The url argument is passed without sanitization, allowing for potential argument injection if a user provides input starting with a hyphen.
- [PROMPT_INJECTION] (LOW): The skill possesses a surface for indirect prompt injection. 1. Ingestion points: The URL argument in scripts/lighthouse_audit.py is used to fetch external data. 2. Boundary markers: No delimiters or warnings are used to separate external data from instructions. 3. Capability inventory: The skill allows access to the Bash tool. 4. Sanitization: There is no validation or sanitization of input URLs or the fetched lighthouse report.
Audit Metadata