nano-banana-edit

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the runcomfy command-line tool to perform image editing tasks. It passes instructions and parameters using a structured JSON string via the --input flag, which mitigates traditional shell injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @runcomfy/cli package from the NPM registry and fetches skill definitions from a GitHub repository (agentspace-so/runcomfy-skills). These are standard operational requirements for integrating with the RunComfy platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external image URLs provided by the user. The documentation identifies image-based prompt injection as an inherent risk of model processing and notes that the CLI environment provides basic boundaries (JSON-only transport) to reduce local execution risks.
  • [DATA_EXPOSURE]: The documentation explains how the RunComfy CLI manages API tokens (storing them in ~/.config/runcomfy/token.json with 0600 permissions) and recommends using the RUNCOMFY_TOKEN environment variable for secure automation in CI/CD environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:56 AM
Security Audit — agent-trust-hub — nano-banana-edit