gemini

Warn

Audited by Snyk on May 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's recipes and tips (e.g., references/recipes.md and SKILL.md) explicitly instruct using Gemini's web search (-e web_search) and include example prompts like "Research the latest React 19 changes and summarize the current sources you use," which indicates the agent will fetch and ingest open/public web content (untrusted third‑party sources) that can influence subsequent decisions and tool use.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 4, 2026, 03:26 PM
Issues
1