tech-blog

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

• Third-party content exposure detected (high risk: 1.00). The skill's required "Research & Verify" step in SKILL.md and the "Doc-Driven Research" section of references/GUIDELINES.md explicitly direct the agent to locate and use external web sources (official docs, vendor blogs, community posts) as untrusted inputs and to cite them—i.e., the agent will fetch and interpret open/public third‑party content as part of its workflow, which can influence its writing decisions.