to-issues

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow can fetch and read full bodies/comments of user-supplied issue references (public/outsider-authored issue text) via “fetch it from the issue tracker and read its full body and comments,” which then becomes LLM context; this is outsider free text ingestion through authenticated GitHub issue content.