forge-brainstorm

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

• Third-party content exposure detected (high risk: 0.90). This skill's Step 1 explicitly tells the agent to check related issues using "gh issue list" (and to look for prior attempts/closed issues), which requires fetching and interpreting public GitHub issues (user-generated, untrusted third‑party content) and using those findings to drive questions and design decisions.