semantic-release-automation

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The GitHub Actions templates reference several external resources, including official actions like actions/checkout@v7 and actions/setup-node@v6, as well as the community action dorny/paths-filter@v4. These are well-known and standard tools for CI/CD workflows.
  • [COMMAND_EXECUTION]: The monorepo template configuration (releaserc.monorepo-package.json) uses the @semantic-release/exec plugin to execute a Node.js one-liner that updates the package.json version field. This is a standard automation pattern for monorepo release management.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted external data in the form of git commit messages and pull request titles to compute version bumps and generate changelogs.
  • Ingestion points: Git commit messages and Pull Request titles as described in SKILL.md.
  • Boundary markers: None explicitly defined in the provided configuration templates to distinguish between instructions and data within commit messages.
  • Capability inventory: The skill has the capability to write to the file system (updating CHANGELOG.md, package.json, and creating git tags) and perform network operations (creating GitHub Releases and publishing packages to npm via GITHUB_TOKEN and NPM_TOKEN).
  • Sanitization: The skill relies on the built-in parsing and sanitization logic of the semantic-release library and its plugins.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 10:14 PM
Security Audit — agent-trust-hub — semantic-release-automation