securitytrails

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md instructs the agent to connect to SecurityTrails via the Membrane CLI and run actions (e.g., fetching WHOIS, DNS, subdomains, and bulk CSV data) which pulls untrusted/public internet content that the agent is expected to read and act on, creating risk of indirect prompt injection.