Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
zimage
v1.0.0使用 Z-Image 轻量级文生图接口生成图片。适用于用户要求“生成图片”“海报图”“封面图”“带中文文字的图片”，或直接说比例如 1:1、16:9、9:16 时。将用户的比例要求转换为 size 参数，按用户要求的数量精确执行且不得重复执行。调用接口 zImage，参数含 prompt（必填）与 size（可选...
⭐ 0· 69·0 current·0 all-time
bycmhan@runninghcm
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's name/description (image generation) matches the behavior in SKILL.md and scripts (calls an image-generation HTTP API). However the registry metadata claims no required environment variables or primary credential, while SKILL.md and the scripts clearly require an X_API_KEY and an on-disk config path (~/.config/z-image/.env). That mismatch between claimed requirements and actual instructions is an incoherence.
Instruction Scope
Runtime instructions are narrowly focused on collecting prompt/size/count, validating them, and calling a fixed external endpoint. They also direct the agent to read an environment variable (X_API_KEY) and a local config file for the key, and to persist a provided key to ~/.config/z-image/.env. Reading/writing the skill's own config file is within scope for persistent credentials, but the instructions also tell the agent to obtain the key from 'kexiangai.com' while the actual API endpoint is 'agent.mathmind.cn' — an endpoint/provider mismatch that should be verified.
Install Mechanism
There is no install specification (instruction-only), and the included scripts are plain shell files. No external downloads, package installs, or archive extraction are present. This is low-risk from an installation-execution perspective.
Credentials
The SKILL.md and scripts require an X_API_KEY and optionally persist it in ~/.config/z-image/.env, but the skill registry metadata declares no required env vars or primary credential. The skill will read environment variables and a user-owned config file — reasonable for an API key but the undeclared credential is a mismatch and the script stores the key in plaintext in the user's home directory (file permissions set to 600, which is better than world-readable but still local plaintext). The skill transmits prompts (potentially sensitive) and the API key to an external endpoint.
Persistence & Privilege
The skill requests to store its own credential under ~/.config/z-image/.env and to read it on subsequent runs. It does not request system-wide config changes, set always:true, or modify other skills. Persisting its own key and creating a dot-dir is normal for this use-case.
What to consider before installing
Before installing or using this skill: 1) Verify and trust the external endpoint (https://agent.mathmind.cn) — confirm that this is the intended API host for the key obtained from kexiangai.com; the mismatch between the key-provider domain and API endpoint is unusual and worth confirming with the skill author or provider. 2) Expect the skill to require an API key (X_API_KEY) despite the registry metadata saying none — do not provide highly privileged or long-lived credentials unless you trust the service. 3) The skill will persist the key in ~/.config/z-image/.env (permission 600) — if you prefer not to store keys on disk, provide the key per-session or use a limited-scope key. 4) Prompts and images are sent to the external API; avoid sending sensitive PII or confidential prompts. 5) If you need higher assurance, ask the author to: (a) correct the registry metadata to declare X_API_KEY as a required credential, (b) explain why the key issuer domain differs from the API host, and (c) optionally support in-memory/session-only keys instead of writing to disk. If you cannot validate those points, proceed cautiously (e.g., test with an expendable key).Like a lobster shell, security has layers — review code before you run it.
latestvk973xz8d8wf9gxan3vzyx5gd25844j1s
License
MIT-0
Free to use, modify, and redistribute. No attribution required.