banana-image

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 can perform Google Search grounding (mentioned in SKILL.md/README and templates/defaults) and the runtime script scripts/banana_image_exec.ts sets config.tools = [{ googleSearch: {} }] when --grounding/enable_grounding is used, so the agent will fetch and consume public web search results (untrusted third‑party content) that can directly influence generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 09:04 AM