http-debugger

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches full request and response bodies from the user's Smello API (e.g., http://localhost:5110/api/requests and http://localhost:5110/api/requests/{id}) which contain arbitrary, untrusted third-party content captured from the open web, and the SKILL.md explicitly instructs the agent to read and interpret those bodies as part of its debugging workflow.