curl-md

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs the agent to fetch and ingest arbitrary public webpages (e.g., via the hosted endpoint https://curl.md/ or the CLI when "the user shares a URL") so untrusted third‑party content is read and can influence the agent's decisions and actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill calls the hosted fetch endpoint https://curl.md/ at runtime to retrieve arbitrary remote pages which are injected into the agent context and thus can directly control prompts/instructions.