CVE

Warn

Audited by Snyk on Mar 10, 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 IdentifyCVE and ResolveCVE workflows explicitly instruct the agent to fetch and read third‑party CVE pages and patches (e.g., "WebFetch https://nvd.nist.gov/vuln/detail/...", WebFetch to raw.githubusercontent.com, mcp__exa__web_search_exa searches, and curl to GitHub commits) and to base triage/patch/whitelist decisions on that content, exposing the agent to untrusted user-generated web content that can materially affect actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 11:33 AM