debug

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

• Third-party content exposure detected (high risk: 0.90). The skill's required probe workflow explicitly runs network fetch probes (e.g., curl -s in Phase 2 and references/failure-taxonomy.md and references/probe-protocol.md) and npm view calls that ingest responses from arbitrary public endpoints, which the agent reads and uses to drive diagnostics and next actions—exposing it to untrusted third‑party content that could carry indirect prompt injection.