cognitive-load-assessment
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 instructs the agent to "Verify concepts via MCP servers (perplexity)," which requires fetching and interpreting content from a public third-party search/aggregation service (Perplexity), exposing the agent to untrusted web-sourced content that could carry indirect prompt injections.
Audit Metadata