action-network
Warn
Audited by Snyk on May 2, 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). The skill's SKILL.md instructs the agent to use the Membrane CLI to connect to Action Network (e.g.,
membrane connect --connectorKey action-networkandmembrane action run/ list/get actions such as list-petitions, get-event, list-petition-signatures) which fetches public, user-generated content from Action Network that the agent is expected to read and could materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata