cv-generator

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can fetch and extract outsider-authored free text from user-supplied LinkedIn URLs / portfolio URLs / GitHub profiles (public web content), which is then ingested into the agent’s LLM context for CV generation (sections “LinkedIn URL”, “Portfolio / personal website”, and “GitHub profile”).