clawddocs

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

• Third-party content exposure detected (high risk: 0.70). The required workflow includes “Fetch the doc: ./scripts/fetch-doc.sh <path> or use browser” which at runtime retrieves documentation text from https://docs.clawd.bot/<path> (public web content), so outsider-authored free text can be ingested into the agent’s LLM context via the fetched page body.