ExtractWisdom
Warn
Audited by Snyk on Mar 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Workflows/Extract.md and SKILL.md explicitly require fetching content from public sources (YouTube via
fabric -y "URL"and Article URLs via "WebFetch") and instruct the agent to deeply read and use that untrusted, user-generated content to decide sections and drive extraction outputs, so third-party content can directly influence the agent's decisions and behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata