Nano Banana Pro (Morfeo)

ReviewAudited by ClawScan on May 1, 2026.

Overview

The skill’s image-generation behavior is coherent and purpose-aligned, but users should notice that it sends prompts/images to Google, uses a Gemini API key, and relies on runtime-installed Python packages.

Before installing, confirm you are comfortable sending selected images and prompts to Google, use a restricted Gemini API key preferably via `GEMINI_API_KEY`, and specify the desired resolution explicitly because the documentation and code disagree on the default.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Medium

#ASI07: Insecure Inter-Agent Communication

What this means

Any image or prompt provided to the skill may be transmitted to Google's API for processing.

Why it was flagged

The script adds user-supplied input images to the request sent to Google's Gemini image model. This is expected for image editing, but it means private images and prompts leave the local machine.

Skill content

parts.append(input_img) ... response = client.models.generate_content(model="gemini-3-pro-image-preview", contents=parts, config=gen_config)

Recommendation

Use this skill only with images and prompts you are comfortable sending to Google, and review the provider's data-use terms for sensitive content.

Low

#ASI03: Identity and Privilege Abuse

What this means

A Gemini API key may allow API usage billed to or quota-limited by the user's account.

Why it was flagged

The skill requires a Gemini API key even though the registry metadata declares no primary credential or required environment variable. The key use is purpose-aligned, but users should understand the credential grants access to their Gemini API account/quota.

Skill content

The script checks for API key in this order:
1. `--api-key` argument
2. `GEMINI_API_KEY` environment variable

Recommendation

Prefer using a restricted Gemini API key through an environment variable, avoid putting keys directly on the command line, and revoke/rotate the key if it is exposed.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Future dependency versions could change behavior or introduce dependency risk, although the dependencies are directly related to the skill's purpose.

Why it was flagged

The script declares runtime dependencies with lower-bound version ranges. When run through `uv`, compatible package versions may be resolved from the package index rather than from a pinned lockfile.

Skill content

# dependencies = [
#     "google-genai>=1.0.0",
#     "pillow>=10.0.0",
# ]

Recommendation

Pin dependency versions or use a reviewed lockfile when installing in sensitive environments.

Info

#ASI09: Human-Agent Trust Exploitation

What this means

If no resolution is specified, the skill may generate larger images than the documentation suggests.

Why it was flagged

The code defaults to 2K output, while the skill description and resolution mapping state that 1K is the default when no resolution is mentioned. This mismatch could affect user expectations, cost, or output size.

Skill content

default="2K",
        help="Output resolution: 1K, 2K (default), or 4K"

Recommendation

Explicitly pass `--resolution 1K`, `2K`, or `4K`, and the publisher should align the documentation and code default.