Nano Banana Pro Image Generation & Editing
View on ClawHub↗70High
Unsanitized user input enables command injection, path
Behavior Analysis
Description verified — behavior matches claim
Claims to do
Nano Banana Pro Image Generation & Editing: Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image).
Actually does
This skill executes a Python script via `uv run` to interact with the Google Nano Banana Pro API (Gemini 3 Pro Image). It takes a text prompt, an optional input image file, and an API key (from argument or `GEMINI_API_KEY` env var). It saves the generated or edited image as a PNG file to the user's current working directory.
Skill Info
Namesteipete/nano-banana-pro
Registryclawhub
Version1.0.1
PURLpkg:clawhub/steipete/nano-banana-pro@1.0.1
Stars338
Downloads86,131
Installs1,764
Source
SHA-2564ea88f4b0e95...
SHA-14d6731a128bf...
MD5eb0735f717c3...
TLSH1ec1d8216c44...
ssdeep96:UE4RpBfXp...
Size5,701 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
ClawHubDocs
openclaw skills install steipete/nano-banana-proAssessments (1)
AI Agent Traps ↗Command execution with user-controlled pathshighcommand execution
The skill executes a Python script via `uv run` with arguments (`--filename`, `--input-image`) that are derived from user input. Without proper sanitization within the `generate_image.py` script, this could lead to path traversal for arbitrary file writes/reads or command injection.
90% confidenceline 13
uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "..." --filename "output-name.png" --input-image "path/to/input.png"
Reconnaissance via file existence checkmediumreconnaissance
The preflight check `test -f "path/to/input.png"` allows checking for the existence of arbitrary files on the system if the `path/to/input.png` argument is fully user-controlled.
80% confidenceline 64
test -f \"path/to/input.png\"
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/clawhub/steipete/nano-banana-pro)HTML
<a href="https://mondoo.com/ai-agent-security/skills/clawhub/steipete/nano-banana-pro"><img src="https://mondoo.com/ai-agent-security/api/badge/clawhub/steipete/nano-banana-pro.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/clawhub/steipete/nano-banana-pro.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow