skills/leek/agent-skills/release/Gen Agent Trust Hub

release

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a suite of standard development tools, including git and the GitHub CLI (gh), to manage project state. These tools are used for repository status checks, committing code, tagging versions, and pushing updates to the remote origin.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external repository remotes via git fetch and git push to ensure the local branch is synchronized with the upstream source before proceeding with a release.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's history and configuration files to automate versioning logic.
  • Ingestion points: Data is pulled from git log output (commit subjects) and various project files like package.json, pyproject.toml, or Cargo.toml (version strings).
  • Boundary markers: The instructions do not specify explicit delimiters to separate this external data from the agent's internal logic.
  • Capability inventory: The agent has the ability to modify local files, commit changes, push to remote servers, and create release entries on GitHub via the gh tool.
  • Sanitization: No specific sanitization or filtering of commit messages is described before they are processed for release note generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 12:11 PM