git-remote-release

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands such as git log, git remote, and git symbolic-ref to resolve the current branch and repository state.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh api) to retrieve commit and pull request metadata from remote repositories.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the GitHub API to fetch data for release note generation. GitHub is recognized as a well-known and trusted service for development workflows.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external sources, representing a surface for indirect prompt injection.
  • Ingestion points: Commit messages and pull request descriptions retrieved from the Git history and GitHub API (SKILL.md).
  • Boundary markers: No explicit markers or instructions to ignore embedded commands are used during the data collection phase.
  • Capability inventory: Uses standard git and gh CLI tools for data retrieval; no write operations or dangerous system-level access is requested.
  • Sanitization: The skill does not explicitly describe sanitization of the retrieved text before summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 07:38 AM
Security Audit — agent-trust-hub — git-remote-release