clairvoyance

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime workflow is to “collect the snapshot” by gathering observable state through legitimate interfaces (e.g., public APIs/status pages/DNS/HTTP headers), which can include outsider-authored free text from public web content fetched at runtime and ingested into the agent’s LLM context.