gemini-3-image-generation

Fail

Audited by Snyk on Feb 15, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt contains code examples that require embedding API keys directly as literal strings (e.g., genai.configure(api_key="YOUR_API_KEY") and new GoogleGenerativeAI("YOUR_API_KEY")), which instructs replacing placeholders with real secrets and thus would require the LLM to handle/output secret values verbatim.

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly enables Google Search grounding (see tools=[{"google_search_retrieval": {}}] in references/grounded-generation.md and scripts/grounded-gen.py), which fetches and uses untrusted public web content as grounding sources for image generation, exposing the agent to potential indirect prompt injection.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 09:39 PM