jt-find-skills

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries an external public registry search API at https://skills.sh/api/search and ingests the resulting skill descriptions and metadata.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill queries an external web API (https://skills.sh/api/search) to retrieve skill recommendations that influence the behavior and options presented to the user, constituting an unverified third-party operational dependency.