deep-research

Fail

Audited by Snyk on Feb 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.


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

  • Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and ingests content from user-provided URLs using "webfetch" and performs联网搜索 via the Task tool that pulls community discussions, GitHub repos and public web pages, so it clearly consumes untrusted public third‑party content.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 07:38 AM