content-director
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via Stage 2/0c trend research that scrapes public social/web pages (e.g., captions/hashtags/text from
scrape_social/capture_website) and then the agent summarizes and includes that information in its prompt context for menu/script generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata