gemini-system

Warn

Audited by Snyk on Mar 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: 0.90). The skill's workflow (SKILL.md and references/lib-research-task.md) explicitly instructs Gemini to use Google Search and fetch public web sources (official docs, GitHub READMEs/issues/discussions, Stack Overflow, blog posts, arbitrary URLs) and to ingest and save those findings for downstream use (e.g., documentation and Codex), so untrusted, user-generated content can be read and materially influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 04:57 AM
Issues
1