camino-hotel-finder

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

• Third-party content exposure detected (high risk: 0.80). The skill issues runtime requests to the external Camino API (https://api.getcamino.ai/query) as shown in SKILL.md and scripts/hotel-finder.sh and ingests the API's JSON "results" and "answer" fields which the agent reads and uses to rank/recommend hotels, so untrusted third‑party content can materially influence agent decisions.