osint

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires web search and URL fetching and its workflows (e.g., SKILL.md "Required minimum: web search + ability to fetch URLs", workflows/person.md and workflows/domain.md) direct the agent to read public third‑party sources such as LinkedIn profiles, corporate websites, crt.sh certificate transparency results and the Wayback Machine — all untrusted/user‑generated or third‑party content that the agent must interpret and that can materially influence its findings and next actions.