Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
t-cpm自定义技能
v1.0.0基于conding-plan-models.json配置的AI强化识图筛选工具，支持关键词三维深度分析、多模型图片识别、严格内容审核、批量图片筛选，自动删除不符合要求的图片。触发场景：(1) 本地图片批量匹配关键词筛选 (2) 图片内容审核/合规校验 (3) 自定义规则图片识别分类 (4) 对接其他图片源的二次筛...
⭐ 0· 58·0 current·0 all-time
byVenwell Chiang@kumamon2019s
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description (AI image filtering with strict rules and optional deletion) matches the code and SKILL.md: it reads a local config for Base URL/API key, calls multimodal models for judgments, and deletes files that don't match. Requiring the model endpoint and key from a local JSON config is coherent with the stated purpose.
Instruction Scope
The runtime will read images from arbitrary user-supplied paths and (by default) permanently delete files judged '不符合'. It also reads a JSON config at an absolute path (/root/.OpenClaw/workspace/conding-plan-models.json) and sends images (embedded as data: URIs / base64) and prompts to the external model endpoint. These actions go beyond passive analysis—they transmit user images externally and perform destructive file operations.
Install Mechanism
There is no install spec and only one Python script; nothing is downloaded or written by an installer. Risk from installation is low.
Credentials
No environment variables are requested, but the script reads an API key and Base URL from a local JSON config file. That is reasonable for contacting models, but it means the skill will use whatever endpoint/key exist in that config—verify that file contains a trusted service. The skill does not request unrelated credentials, but it does access a fixed config path which could contain user secrets for other tooling if colocated.
Persistence & Privilege
The skill does not request 'always: true' and does not modify other skills or system settings. It runs only when invoked. However, autonomous model invocation (allowed) combined with the deletion behavior increases blast radius if misused.
What to consider before installing
This skill will upload your images (base64-embedded) to the model endpoint specified in /root/.OpenClaw/workspace/conding-plan-models.json and — by default — permanently delete images judged non-conforming. Before installing or running: 1) Inspect the config file and confirm the Base URL and API key point to a trusted service; 2) Do not run with production or sensitive images until you validate behavior; run with --delete_invalid False and test on a small sample first; 3) Backup any images or directories you run this on (deletion is permanent); 4) Consider running the script in an isolated environment or container and review network activity to ensure images are not sent to an unexpected endpoint; 5) If you cannot verify the endpoint or if policy forbids uploading images, do not use this skill. If you want help checking the config file format or testing safely, provide a redacted sample and I can advise further.Like a lobster shell, security has layers — review code before you run it.
latestvk973tge49gb2h81z1yrgfrtzp983zqe5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.