camino-safety-checker

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

• Third-party content exposure detected (high risk: 0.70). The skill's runtime workflow (scripts/safety-checker.sh and SKILL.md) sends location/context to and ingests the JSON response from the external API endpoint https://api.getcamino.ai/context, and the returned free-text fields (area_description, context_insights, place entries) are read and used to drive safety decisions, exposing the agent to untrusted third-party content that could influence actions.