gradeus
Warn
Audited by Snyk on Apr 28, 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 describes using Membrane to connect to Grade.us and run actions like "List Reviews" which fetches user-generated reviews and other third-party content from Grade.us (https://apidocs.grade.us/), meaning the agent will ingest untrusted public content as part of its workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata