find-skills

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

• Third-party content exposure detected (low risk: 0.10). The skill searches and installs packages from public or private registries (skills.sh or a Nacos-based registry), which represents community/registry search input without forced delivery.

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

• Potentially malicious external URL detected (high risk: 0.70). The script fetches credential data from an arbitrary controller URL via an unvalidated environment variable, constituting a weak remote operational dependency.