rf-restinstance

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and example files (e.g., assets/examples/basic-rest.robot and many examples using Library REST https://jsonplaceholder.typicode.com and other external API URLs) instruct the agent to fetch and parse responses from public, user-facing HTTP endpoints and to use response fields (tokens, IDs, statuses) to drive subsequent requests and decisions, which exposes it to untrusted third‑party content that could influence behavior.