diagnose
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime, the skill’s Layer 1
external-check-agentperforms WebSearch and ingests fetched public web page snippets/results into the agent context to populate the “External Factor Scan” table (outsider-authored free text from the public web).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata