ai-coding-agents-tools
Warn
Audited by Snyk on Aug 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). ToolSearch and the execution pipeline are designed to accept model-supplied free text (e.g., the ToolSearch
querystring) and return tool schemas/results, which creates an indirect prompt-injection surface if outsider-authored text can influence those strings.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata