saudi-address
Warn
Audited by Snyk on Jul 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). SKILL.md instructs runtime
curlcalls to a public “freetextsearch” endpoint with user-suppliedSEARCH_TEXT, and the resulting free-text search responses would be ingested as readable text by the agent/LLM (indirect prompt-injection risk from outsider-authored API content).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata