github-repo-analyzer

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCREDENTIALS_UNSAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill clones and analyzes untrusted third-party content from external GitHub repositories, creating a risk for indirect prompt injection.\n
  • Ingestion points: The git clone operation in the workflow downloads external repository content into a local directory for analysis.\n
  • Boundary markers: Absent; there are no explicit instructions to the AI to ignore embedded commands or instructions found within the repository files.\n
  • Capability inventory: The skill executes shell commands via git (in scripts/repo_info.py) and performs network requests to api.notion.com (in scripts/notion_sync.py).\n
  • Sanitization: The skill does not perform filtering or sanitization of repository content before it is processed by analysis tools.\n- [CREDENTIALS_UNSAFE]: The script scripts/notion_sync.py reads a sensitive credential from ~/.config/notion/api_key. While this is the intended configuration method for the Notion integration, it involves accessing a sensitive file path.\n- [COMMAND_EXECUTION]: The script scripts/repo_info.py utilizes the subprocess module to execute git commands for extracting repository metadata and statistics.\n- [EXTERNAL_DOWNLOADS]: The skill uses git clone to download source code from arbitrary GitHub repositories provided by the user as part of its core functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 12:02 AM