eliteforge-qingtui-cli
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and interface explicitly instruct the agent to run qingtui list-users and qingtui resolve-users against the (public) QingTui API (default https://open.qingtui.com), ingesting untrusted user-generated data (user lists/open_ids) which the agent parses and then uses to decide and perform actions (send-text), so third-party content can materially influence tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata