economics
Warn
Audited by Snyk on Mar 8, 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.md Step 2 explicitly instructs the agent to "Search the web for current pricing for every model you use" (e.g., site:openai.com, site:anthropic.com, site:ai.google.dev), which requires fetching and interpreting public third-party web pages whose content will directly influence pricing calculations and downstream decisions.
Audit Metadata