github-release-management

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated GitHub content (e.g., "gh pr list --state merged ..." and "gh api repos/:owner/:repo/compare/...") in the main workflows and GitHub Actions steps and then uses those PRs/commit messages to generate changelogs, suggest versions, and drive automated release actions, so untrusted third-party content can materially influence agent decisions and tool use.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill repeatedly runs "npx claude-flow@alpha" (which fetches and executes package code from the npm registry, e.g. https://registry.npmjs.org) at runtime to orchestrate AI agents and generate prompts/instructions, so remote code is fetched-and-executed and controls agent behavior.