release
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of
gitandgh(GitHub CLI) to manage branches, generate release notes, create tags, and monitor GitHub Action runs. A Python helper script (changelog_entry.py) also usessubprocess.check_outputto interact with the GitHub API viagh. The script uses a list for command arguments, which is a secure practice to prevent shell injection.\n- [EXTERNAL_DOWNLOADS]: The skill usesnpx --yes mint@latestto download and execute the Mintlify documentation validator from the NPM registry. It also usescurlto fetch metadata frompypi.organd check deployment status ongofastmcp.com, both of which are trusted or vendor-owned services.\n- [INDIRECT_PROMPT_INJECTION]: The release process involves ingesting untrusted data from GitHub PR titles and user-provided release notes. The included scriptchangelog_entry.pyimplements MDX/JSX escaping to prevent malicious or malformed strings from interfering with the documentation build.\n - Ingestion points: GitHub API
generate-notesoutput and local temporary files containing release notes.\n - Boundary markers: None explicitly used in the prompt instructions; however, the Python script performs programmatic escaping of control characters.\n
- Capability inventory: The skill has the capability to write to local documentation files and push changes/merge PRs to the vendor repository.\n
- Sanitization: The
escape_mdxfunction in the helper script backtick-wraps potentially problematic characters (e.g.,<,{,}) to ensure they are treated as literals in the MDX output.
Audit Metadata