rules-from-coding-agent-failures

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

• Third-party content exposure detected (high risk: 0.78). The required runtime workflow (“triage/promotion” via grep over docs/reflection-log/[0-9]*.md) ingests the body text of reflection-log entries authored by repo contributors (outsider-authored relative to the operating user), which then becomes LLM-readable context used to propose rules/hooks/gates.