nano-banana-2
Fail
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill defines several patterns for executing the
runcomfyCLI tool where user-provided input is interpolated directly into a shell command line (e.g.,runcomfy run ... --input '{"prompt": "<user prompt>"}'). This is a classic command injection vulnerability; if a user provides a prompt containing a single quote or shell meta-characters (like'; touch /tmp/pwned; '), the agent will generate a command that executes arbitrary shell code on the user's machine. - [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install an external dependency, the
@runcomfy/cliNode.js package, usingnpm i -g @runcomfy/cli. It also downloads generated image assets from remote domains (runcomfy.netandruncomfy.com) to a user-specified local directory. - [DATA_EXFILTRATION]: The skill interacts with sensitive local data by reading an API token from
~/.config/runcomfy/token.jsonor theRUNCOMFY_TOKENenvironment variable. While this is necessary for the service to function, the combination of this access with the command injection risk and the ability to specify an arbitrary--output-dir(which could allow overwriting sensitive system files) presents a significant security surface.
Recommendations
- AI detected serious security threats
Audit Metadata