copy-assistant

Warn

Audited by Snyk on Mar 11, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly requires calling a search/verification tool ("搜索验证步骤" using aisearch-mcp-server__chatCompletions) to fetch and incorporate web search results into edits, so the agent will ingest untrusted public search/web content that can change its outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 07:09 AM