cv-generator

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow includes fetching and extracting text from outsider-authored public web content (e.g., “Portfolio / personal website” and “LinkedIn profile URL” pages) and then ingesting that extracted prose into the agent for CV generation, which is an indirect prompt-injection exposure path.