changelog-automation

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references standard development dependencies from well-known package registries.
  • Fetches packages such as @commitlint/cli, husky, and semantic-release from the npm registry.
  • Fetches the commitizen package from the PyPI registry.
  • Incorporates official GitHub Actions for workflow automation, including actions/checkout and actions/setup-node.
  • [COMMAND_EXECUTION]: Provides standard shell commands for initializing project configurations and running automation scripts.
  • Includes commands for installing packages, creating configuration files (e.g., commitlint.config.js), and setting up Git hooks via Husky.
  • Utilizes environment variables for secure token handling within GitHub Actions workflows (e.g., GITHUB_TOKEN, NPM_TOKEN), which is a recommended security practice.
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that processes external strings (commit messages and PR content) to generate documentation.
  • Ingestion points: Commit messages, Pull Request titles, and Pull Request descriptions (Method 5, Method 6).
  • Boundary markers: None explicitly defined in the provided configuration templates.
  • Capability inventory: File system writes (CHANGELOG.md), Git push operations, and GitHub Release creation.
  • Sanitization: Relies on the inherent processing logic of the established third-party tools (e.g., semantic-release, git-cliff).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 12:59 PM