lead-signals

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads public social media posts, comments, reviews, job postings, and news articles from external web platforms via API/search tools, ingesting outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches instructions and setup scripts from an unknown third-party domain (treg.to) at runtime, representing a weak operational dependency.