wind-mcp-skill

Warn

Audited by Snyk on May 13, 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 async update-check (scripts/update-check.mjs) calls public GitHub/Gitee tree APIs and cli.mjs's maybePrintUpdateNotice prints upgrade commands from that fetched repo data to stderr — and SKILL.md explicitly instructs the agent to relay those update notices to users — meaning untrusted, public repository content can be ingested at runtime and influence agent behavior.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 13, 2026, 05:16 AM
Issues
1