non-linear

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: 1.00). The skill explicitly calls open-web search tools (e.g., exa:web_search_exa in references/MCP-INTEGRATION.md and the searchCurrentInformation/gatherEvidence patterns) and integrates returned page text/URLs into subagent outputs and the NoisyGraph, so it ingests and interprets untrusted public web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:12 AM