skills/prefecthq/fastmcp/release/Gen Agent Trust Hub

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 git and gh (GitHub CLI) to manage branches, generate release notes, create tags, and monitor GitHub Action runs. A Python helper script (changelog_entry.py) also uses subprocess.check_output to interact with the GitHub API via gh. The script uses a list for command arguments, which is a secure practice to prevent shell injection.\n- [EXTERNAL_DOWNLOADS]: The skill uses npx --yes mint@latest to download and execute the Mintlify documentation validator from the NPM registry. It also uses curl to fetch metadata from pypi.org and check deployment status on gofastmcp.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 script changelog_entry.py implements MDX/JSX escaping to prevent malicious or malformed strings from interfering with the documentation build.\n
  • Ingestion points: GitHub API generate-notes output 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_mdx function in the helper script backtick-wraps potentially problematic characters (e.g., <, {, }) to ensure they are treated as literals in the MDX output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 07:40 PM
Security Audit — agent-trust-hub — release