Vision Sandbox

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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.

Note

ASI05: Unexpected Code Execution

What this means

Gemini may generate and run Python in Google's sandbox to analyze the uploaded image, and the generated code/output may be printed back to the user.

Why it was flagged

The tool explicitly enables Gemini's native code execution capability. This is central to the stated visual-verification purpose and is described as Google-hosted sandbox execution, not local execution of model-generated code.

Skill content

tools=[types.Tool(code_execution=types.ToolCodeExecution())]

Recommendation

Use this only for intended visual-analysis tasks, and do not treat generated code or model output as inherently trusted without review.

Note

ASI07: Insecure Inter-Agent Communication

What this means

Any screenshot or image you choose may leave your machine and be processed by Google Gemini.

Why it was flagged

The implementation sends the user prompt and selected image part to the external Gemini API. This is disclosed and purpose-aligned, but it is still an external provider data flow.

Skill content

response = client.models.generate_content(
            model=model_id, contents=[prompt, image_part], config=config
        )

Recommendation

Avoid using confidential screenshots or sensitive images unless you are comfortable with Gemini's API data handling for your account.

Note

ASI03: Identity and Privilege Abuse

What this means

The skill can make Gemini API calls billed or governed under the account associated with the configured key.

Why it was flagged

The skill requires a Gemini API key and uses it to create a Gemini client. The artifacts do not show hardcoded keys, logging of the key, or unrelated credential use.

Skill content

api_key = os.getenv("GEMINI_API_KEY")
...
client = genai.Client(api_key=api_key)

Recommendation

Use a Gemini API key with appropriate account limits and rotate it if you suspect it has been exposed.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installing later dependency versions could alter the runtime behavior of the skill.

Why it was flagged

The package depends on a version-ranged external library rather than a pinned version. This is normal for many Python projects, but it means future dependency versions could change behavior.

Skill content

dependencies = [
    "google-genai>=1.0.0",
]

Recommendation

Prefer a locked environment or pinned dependency versions for repeatable installs, especially in sensitive workflows.