search-pi-extensions

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/search_pi_extensions.py executes the gh (GitHub) CLI tool to fetch repository metadata such as stars and activity. The inputs used in the command (owner and repository name) are properly sanitized using urllib.parse.quote() before being incorporated into the API path, which prevents command injection attacks. Additionally, the subprocess call does not use a shell, further reducing risk.
  • [SAFE]: The skill processes data from the public npm registry and GitHub. This functionality involves ingesting untrusted external content (package descriptions and keywords). While this represents a surface for indirect prompt injection, the impact is limited because the LLM's role is restricted to quality assessment and summarization for the user. No sensitive data is exposed, and there is no automated execution of the downloaded content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 10:49 AM
Security Audit — agent-trust-hub — search-pi-extensions