docs-guide-knowledge

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md and references/fallback-strategies.md) explicitly fetches and parses open/public third‑party documentation — e.g., trying {site}/llms.txt, GitHub raw markdown, sitemap.xml and WebSearch — and then reads/extracts sections and code examples from those pages to drive answers, so untrusted external content can materially influence the agent's behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches external documentation at runtime — e.g., GitHub raw URLs like https://raw.githubusercontent.com/{owner}/{repo}/main/docs/{file}.md — and injects that content into the model context to form responses, so remote content can directly control agent prompts.