Nano Banana Image T8

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-aligned for image generation/editing, but users should know it stores a Nano Banana API key and sends prompts/images to a third-party API.

This skill is reasonable for its stated purpose if you trust the Nano Banana/T8 API provider. Before installing, understand that it can save your API key locally, reuse it later, and upload your prompts and images to https://ai.t8star.cn. Avoid overriding the API base URL and remove the saved credential if you stop using the skill.

VirusTotal

35/35 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

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.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

Someone using this skill later may be able to call the image API with the saved key without re-entering it.

Why it was flagged

The skill is designed to store a user API key locally and reuse it later. This is expected for the API integration, but it grants continuing access to the user's Nano Banana account/API quota.

Skill content
saved_file: "~/.whaleclaw/credentials/nano_banana_api_key.txt" ... 下次若用户未提供 Key,可直接使用已保存 Key
Recommendation

Install only if you are comfortable with local key persistence; revoke or delete the saved key file if you no longer want the skill to use it.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

Prompts and input images may be processed by the third-party API provider.

Why it was flagged

The script sends prompts and uploaded image files to an external image-editing endpoint. This is central to the skill's purpose, but it means user content leaves the local environment.

Skill content
resp = client.post(f"{base_url}/v1/images/edits", data=form_data, files=files, timeout=300)
Recommendation

Do not use sensitive or private images/prompts unless you trust the provider and its data handling terms.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

If the endpoint were changed, the API key, prompts, and images could be sent to a different service.

Why it was flagged

The instructions say the API host must remain fixed, while also documenting a base-url option. The default and instructions are bounded, but changing this endpoint would redirect API-key-authenticated requests.

Skill content
API 基地址固定为 `https://ai.t8star.cn`,禁止改为其它域名 ... `--base-url`:默认 `https://ai.t8star.cn`
Recommendation

Keep the base URL on the documented provider and do not follow requests to override it unless you intentionally trust the alternate endpoint.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Users have less external provenance information and may not see the credential requirement from metadata alone.

Why it was flagged

The registry metadata lacks source/homepage provenance and does not declare the credential/env-var behavior that SKILL.md describes. This is an under-declared metadata/provenance issue rather than evidence of hidden malicious behavior.

Skill content
Source: unknown; Homepage: none ... Primary credential: none ... Env var declarations: none
Recommendation

Review the SKILL.md and script before installing, and prefer a version whose registry metadata declares its API key and provider requirements.