to-issues

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md step 2 says that if the user passes an issue reference (URL/number/path), the workflow fetches the issue tracker and reads the full body and comments, which are outsider-authored free text that can be ingested into the agent’s LLM context at runtime.