research-pro

Warn

Audited by Snyk on May 12, 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 Pro" flow explicitly spawns a sub-agent to run the Gemini CLI to "research" topics (including "Key Resources/Links") and the included ecosystem-evaluation.md explicitly states the investigation used "web_search + web_fetch", indicating the agent will fetch and read public web sources (e.g., GitHub, Sketchfab) whose untrusted content could influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 12, 2026, 08:05 AM
Issues
1