easy-project
Warn
Audited by Snyk on Apr 30, 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). SKILL.md explicitly instructs the agent to fetch and process external Easy Project data (e.g., via "membrane action list" and "membrane request CONNECTION_ID /path/to/endpoint") — including user-generated issues/projects — which the agent is expected to read and use to decide and perform subsequent actions, so untrusted third‑party content can influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata