baoyu-post-to-wechat
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to prompt for WECHAT_APP_ID and WECHAT_APP_SECRET and then write those values verbatim into a .env file (and potentially include them in subsequent commands), requiring the LLM to handle and output secret values directly.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill actively downloads and ingests arbitrary HTTP/HTTPS resources referenced by user markdown (scripts/md-to-wechat.ts: downloadFile/resolveImagePath) and fetches PlantUML SVGs from an external server (scripts/md/extensions/plantuml.ts: fetchSvgContent), so it reads untrusted third-party content (public URLs) as part of its publishing workflow.
Audit Metadata