force-multiplier

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

• Third-party content exposure detected (high risk: 0.85). The required workflow performs per-target operations on GitHub repos (e.g., reading repo files like CLAUDE.md and .github/PULL_REQUEST_TEMPLATE.md during PILOT/FAN-OUT), which are outsider-authored free text sources that get ingested into the agent LLM context as untrusted data.