skill-design

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 2 "Run web research — execute all 3 searches") explicitly instructs the agent to fetch and extract findings from public third‑party sites (e.g., GitHub via site:github.com and "awesome-claude-code"), and those findings are used to generate options and the final spec, so untrusted user-generated content can materially influence decisions and actions.