gemma-dev
Warn
Audited by Snyk on Jun 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to call fetch_url at runtime to retrieve documentation pages (e.g., https://ai.google.dev/gemma/docs/llms.txt and https://ai.google.dev/gemma/docs/core/prompt-formatting-gemma4.md.txt), and those fetched docs are used to determine prompt formatting and agent behavior, so they are runtime external dependencies that directly control prompts.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata