gemini-system

Warn

Audited by Snyk on Feb 26, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs using "Google Search grounding" and templates to fetch and analyze public web resources (e.g., GitHub READMEs, Issues/Discussions, Stack Overflow, PyPI, blogs) as shown in SKILL.md and references/lib-research-task.md, meaning untrusted third‑party content is ingested and can influence agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 08:07 PM