company-research
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly requires fetching and synthesizing content from publicly available third-party sources (e.g., LinkedIn company pages, Crunchbase/PitchBook, Wikipedia, earnings call transcripts, podcast interviews, Glassdoor, Product Hunt), and the agent is expected to read and interpret those untrusted/user-generated materials as part of its research workflow, which could enable indirect prompt injection.
Audit Metadata