market-research
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow ingests outsider-authored free text when it “searches/uses sources” such as public web content (e.g., analyst/media/blog posts, scraped pages, app-store listings, reviews) and then includes their text in the LLM’s evidence/findings sections.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata