runbook
Warn
Audited by Snyk on Jul 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow includes “External Research (librarian agent)” which at runtime likely fetches/uses public web content (outsider-authored free text) to inform the generated runbook, creating indirect prompt-injection exposure as that research content would be fed into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata