nano-banana-2

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides command templates for interacting with the runcomfy CLI tool to perform model runs locally.
  • [EXTERNAL_DOWNLOADS]: The skill specifies downloading generated content from official RunComfy domains (*.runcomfy.net and *.runcomfy.com).
  • [PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection via user-supplied content.
  • Ingestion points: Untrusted text prompts and media resource URLs are ingested through the CLI's --input parameter as shown in the file SKILL.md.
  • Boundary markers: The instructions recommend passing data via JSON-formatted strings, which helps prevent shell command injection by encapsulating the user input.
  • Capability inventory: The skill utilizes the runcomfy CLI which has the capability to perform network requests and write files to the local file system.
  • Sanitization: There is no evidence of input validation or sanitization within the skill instructions, though it notes that the CLI itself avoids shell expansion.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:57 AM
Security Audit — agent-trust-hub — nano-banana-2