github-release-management

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests user-generated GitHub data (e.g., "gh pr list --state merged ..." and "gh api repos/:owner/:repo/compare...") and then feeds those PRs/commit messages into the AI changelog/release-generation workflow (see the npx claude-flow github changelog steps), exposing the agent to untrusted third-party content that could carry indirect prompt injections.