gh-project-board

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gh command-line tool to interact with GitHub Projects and executes a bundled Node.js script (setup-gh-project-board.mjs) for project normalization.
  • [DATA_EXFILTRATION]: The skill fetches metadata from the user's GitHub projects, including project titles, field names, and select options, to perform audits and suggest normalization plans.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: External data is ingested from the GitHub API, specifically project titles and field configuration labels (file: scripts/setup-gh-project-board.mjs).
  • Boundary markers: Not present; the script treats GitHub data as authoritative for the purposes of comparison, though results are presented to the user for review.
  • Capability inventory: The script has the capability to modify project fields via the GitHub GraphQL API using the gh CLI (file: scripts/setup-gh-project-board.mjs).
  • Sanitization: The script uses JSON.stringify to escape and sanitize string values before they are interpolated into GraphQL mutations, which prevents malformed query injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — gh-project-board