he-code-review

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the skill’s runtime ingestion of “review target” artifacts such as PR bodies, issue text, and “review threads” (outsider-authored) as untrusted evidence in the procedure/contract (e.g., step 3 and inputs include PR/issue/thread text).