triage

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text is ingested via gh issue view <number> ... --json ... body in Step 3, where the issue body is authored by non-operating users (GitHub issue text) and is then passed to subagents (validator/dup-detector/researcher) as LLM-readable prompt content.