assess-ai

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The workflow's Step 3 explicitly instructs the agent to "Research AI safety frameworks using MCP servers (perplexity for NIST AI RMF, EU AI Act guidance)," which requires fetching and interpreting third‑party web content (perplexity/MCP) that can materially influence the agent's assessment decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 04:21 AM