performance-profiling

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/lighthouse_audit.py executes the lighthouse command-line tool to perform audits. This implementation is secure as it uses subprocess.run with a list of arguments, ensuring that user-provided URLs are treated as data rather than shell commands, effectively preventing command injection attacks.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection because it processes content from external URLs via the Lighthouse audit tool. However, the risk is mitigated because the script only extracts structured JSON data (scores and category summaries) and does not interpret or re-execute natural language content from the target pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 10:22 AM