best-practice-guide

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md and references/README.md explicitly instruct agents to use web search tools (searxng_searxng_web_search, searxng_web_url_read) to fetch and synthesize public/ community sources (e.g., Stack Overflow, blogs, official sites) into guides that will be read and used to drive guide generation and integration, which clearly exposes the agent to untrusted third-party content that can influence actions.