ctf-osint

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs fetching and parsing public, user-generated third‑party content—e.g., Twitter/X profiles and archived pages via the Wayback Machine, Tumblr avatars/pages, public Google Docs/Sheets, Pastebin and other social media sites—and expects the agent to read and interpret that content as part of its OSINT workflow, exposing it to untrusted external input.