kimi-skills-finder

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

• Third-party content exposure detected (high risk: 0.85). At runtime, Step 3.2 uses the web_search tool to fetch GitHub results (outsider-authored README/SKILL.md text from public repositories) and Step 3.3 uses browser_visit to read SkillHub pages (outsider-authored skill descriptions), both of which can be ingested as free-form text into the agent’s LLM context.