scenarios
Warn
Audited by Snyk on Apr 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to fetch external documentation (e.g., https://langwatch.ai/scenario/advanced/red-teaming.md and https://langwatch.ai/scenario/llms.txt) via fetch_scenario_docs, and those fetched documents are required and would directly control prompts/instructions for scenario and red-team runs, creating a high-risk runtime dependency.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata