helios-core
Warn
Audited by Snyk on Mar 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: 0.70). The SKILL.md shows runtime fetching/ingestion of external resources (e.g., the Stability Registry example using helios.registerStabilityCheck(fetch('/data.json')...) and schema fields that accept model/json/shader URLs), indicating the agent can load and process arbitrary user-supplied third-party URLs which can influence rendering/behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata