21st-ai
Warn
Audited by Snyk on Jul 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow (“21st generate/iterate/take”) sends the user’s prompt/spec to the 21st service and returns generated “copy-prompt”/HTML, which is outsider-authored free text produced at runtime by an external model/service and then ingested into the agent context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata