write-concept
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: 0.90). The Research step explicitly instructs the agent to perform a WebSearch ("[country] [subject] curriculum [grade]") and find/extract content from official curriculum documents on the open web, i.e., untrusted third-party websites the agent will read and interpret.
Audit Metadata