AGENT LAB: SKILLS

mcp-vods

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's vods_search tool explicitly searches "多个源站" (multiple external source sites) to gather video/playback URLs from public websites, so the agent will fetch and interpret untrusted third-party content from the open web.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:18 PM