command-creator

Warn

Audited by Snyk on Mar 7, 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 "Research Gate (Exa + arXiv — BOTH MANDATORY)" section explicitly requires using mcp__Exa__web_search_exa and WebFetch (e.g., arxiv.org) to fetch and ingest public web content, so the agent will read untrusted third‑party pages as part of its workflow and use that research to drive decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 12:38 AM