find-skills-scoped

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

• Third-party content exposure detected (high risk: 0.80). This skill instructs the agent to search and present skills from the open agent ecosystem (e.g., via npx skills find and links to https://skills.sh/ and GitHub repos), which requires fetching and interpreting untrusted public third‑party skill/repo content as part of its workflow.