huly-assist
Warn
Audited by Snyk on Mar 25, 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's required workflow (SKILL.md) explicitly reads user-generated workspace content via the HULY_HOST CLI commands (e.g., "huly docs read", "huly tasks", "huly task ...", "huly docs list"), meaning it fetches and interprets documents and task descriptions from a third-party Huly instance that could contain untrusted instructions affecting agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata