find-vc-backed-ai-jobs-munich

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 performs direct web search and opens third-party job/company pages and aggregators (e.g., “Direct web search by title and location” and “Specialized job boards”), where the LLM ingests outsider-authored free text such as job descriptions, company/about text, and postings from non-user parties.