ctf-recon

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs fetching and parsing arbitrary public web targets (e.g., numerous curl/ffuf/gobuster commands against "http://target/" and related URLs, JS bundles, .git, APIs, GraphQL endpoints), which ingests untrusted, user-generated third‑party content that the agent is expected to read and interpret.