sdk-docs-auditor

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

• Third-party content exposure detected (high risk: 0.85). The skill fetches arbitrary outsider-authored free text from the target docs site at runtime via curl (e.g., curl -s "<docs_url>/llms.txt" and then curl -s "<docs_url>/<page>" | ... strip HTML to plain text), which is then inserted into the agent’s LLM context for auditing.