modal
Warn
Audited by Snyk on Jun 27, 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 skill’s runtime workflow can ingest outsider-authored free text via
@modal.web_endpoint()request bodies (e.g.,predict(data: dict)/protected(token)), where HTTP clients are not the operating user and their JSON/text becomes LLM-visible input to the function/agent context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata