issue

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

• Third-party content exposure detected (low risk: 0.10). In the issue skill workflow, outsider free text from the user (the “free-text description plus session context”) is used to draft an issue title/body and may be further processed by the optional grilling interview engine (steps 4-6), but the only outsider-posted free text directly ingested at runtime is the human’s own input—not third-party forge/queue text.