tidymydesktop

Warn

Audited by Snyk on Feb 15, 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 explicitly performs web searches for unknown software (see SKILL.md "使用 WebSearch 搜索软件信息" and README "搜索增强" and scripts/classify.js which generates search queries with the --search option), so the agent will fetch and interpret open web (untrusted, third‑party) content as part of its classification workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:30 PM