playbook-lookalikes
Warn
Audited by Snyk on Aug 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In Workflow B, the agent runs prompt B after ingesting outsider-authored free text from scraped company homepages via the
scrape-website(liveness) node, which depends on{{description}}/homepage content that can include attacker-controlled instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata