truefoundry-gateway
Warn
Audited by Snyk on Jul 23, 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 includes querying and then presenting gateway “spans” (request traces) from the spans API (e.g.,
$TFY_API_SH POST /api/svc/v1/spans/query), whose responses can contain free-text request/response payloads (tfy.input/tfy.output), which are outsider-authored user content injected into the LLM context when the agent formats and relays the results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata