gh-oss-release

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage software releases. It uses gh api to fetch repository commits, gh release create to automate tag and release generation, and git commands (pull, add, commit, push) to update a Homebrew tap repository at ~/ghq/github.com/jackchuka/homebrew-tap. It also executes make update within the local tap directory to process formulae updates.
  • [PROMPT_INJECTION]: The skill processes untrusted commit message data which presents an indirect prompt injection surface.
  • Ingestion points: Commit messages from external repositories are fetched via gh api and analyzed in SKILL.md (Step 2).
  • Boundary markers: The workflow does not utilize specific delimiters or instructions to prevent the agent from interpreting commit message content as instructions.
  • Capability inventory: The agent has capabilities to create GitHub releases, push to remote repositories, and execute local make commands.
  • Sanitization: No explicit filtering or validation logic is applied to the ingested commit messages before they are processed for semver classification.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 11:22 AM