Brand Name Oracle
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 instructs the agent to fetch and analyze public web content (using WebFetch/WebSearch and whois) — e.g., social handles, public websites, USPTO TESS and searches for similar companies — which are untrusted third-party sources the agent must read and interpret.
Audit Metadata