find-skills

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

• Third-party content exposure detected (low risk: 0.10). The skill’s workflow described in SKILL.md uses a CLI search/browse flow (e.g., npx skills find [query] against skills.sh / GitHub) but it does not specify ingesting arbitrary outsider-authored free-text payloads into the LLM for further reasoning; it is primarily about selecting skills from search results and recommending commands.