riddle-quiz-maker
Warn
Audited by Snyk on Apr 22, 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.md explicitly instructs the agent to use Membrane to proxy requests to the public Riddle Quiz Maker API (see "Proxy requests" / "Running actions" sections such as
membrane request CONNECTION_ID /path/to/endpointand action list/run), which fetches user-generated quizzes/questions from an external site that the agent is expected to read and which can influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata