project-overview
Warn
Audited by Snyk on Mar 10, 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 describes the Platform Agent monitoring WeChat conversations (see "WeChat Message Monitoring" and the Data Flow Design) and sending extracted user messages to the Rust Orchestrator/DeepSeek for reply generation and automated input insertion, which means untrusted, user-generated messages are ingested at runtime and can materially influence actions.
Audit Metadata