autonomous-coding-agent

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

• Third-party content exposure detected (high risk: 0.80). This skill's "GitHub Actions Integration" example directly feeds github.event.issue.body into the Claude prompt (claude -p "Fix the failing test in ${{ github.event.issue.body }}"), meaning it ingests untrusted, user-generated GitHub issue content that can materially influence agent actions and tool use.