adr
Warn
Audited by Snyk on Feb 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: 0.80). The skill explicitly directs the agent to "Use WebSearch for current best practices" as part of its research support, which means it may fetch and read open/public web content (blogs, forums, Q&A) that is untrusted or user-generated and incorporate it into the ADR workflow.
Audit Metadata