cv-generator

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests outsider-authored profile pages and portfolio websites via direct URL fetching or file uploads based on user instruction.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching external web pages (LinkedIn profiles and portfolios) at runtime, which constitutes an unverifiable runtime external dependency under the dependency gate.