groundhogg
Warn
Audited by Snyk on Apr 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md shows it fetches data from a GroundHogg instance via Membrane (e.g., "List Notes", "Get Contact" actions and the "membrane request CONNECTION_ID /path" proxy), which ingests user-generated/untrusted CRM content that the agent is expected to read and that could materially affect subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata