read

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches arbitrary web pages and URLs via local extraction or optional third-party services, which exposes the agent to outsider-authored free text at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script fetches content from third-party proxy services (https://defuddle.md/ and https://r.jina.ai/) when user opt-in is enabled, constituting a common/reputable unofficial operational dependency.