apiclaw

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and openapi-reference.md explicitly instruct the agent to call apiclaw API endpoints (e.g., reviews/analyze and realtime/product) that ingest Amazon product pages and user-generated reviews, which the agent is expected to read and use to drive analysis and decisions, exposing it to untrusted third-party content.