felo-search

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

• Third-party content exposure detected (high risk: 0.80). This skill's runtime invokes the third-party Felo API (scripts/search.sh posts to https://openapi.felo.ai/v2/chat) and the SKILL.md requires the agent to parse and present the API's "answer" and "query_analysis" (real-time web search results), meaning untrusted/public web-sourced content is ingested and used to drive the agent's responses and decisions.