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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 26, 2026, 12:10 AM
Issues
1
Security Audit — snyk — runbook