axiom-health

Warn

Audited by Snyk on Apr 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: 0.70). The skill explicitly instructs ingesting and parsing third-party clinical FHIR data (see skills/clinical-and-mobility.md and the parse(resource: HKFHIRResource) example, which references HKFHIRResource.data and sourceURL) — these are provider/user‑supplied, untrusted payloads that the agent is expected to read and that can materially affect behavior (displaying clinical event dates, parsing fields, etc.).

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 23, 2026, 09:33 PM
Issues
1