CD scnet-ocr
将图片中的文字、通用文字识别, 票据混贴识别, 印章文字识别, 表格识别, 居民身份证, 银行卡, 社保卡, 户口本, 出生医学证明, 往来港澳通行证, 往来台湾通行证, 台湾居民来往大陆通行证, 港澳居民来往内地通行证, 中国香港身份证, 外国人永久居留身份证, 结婚证, 不动产权证书, 机动车行驶证正页, 机动车行驶证副页, 机动车驾驶证正页, 机动车驾驶证副页, 中国护照, 学历证书, 学历证书电子注册备案表, 学位证书。营业执照, 社会团体法人登记证书, 工会法人资格证书, 宗教活动场所登记证, 民办非企业单位登记证书, 事业单位法人证书, 统一社会信用代码证书, 财务票据统一识别, 食品经营许可证, 食品生产许可证, 卫生许可证, 金融许可证, 金融机构代码证, 支付业务许可证, 开户许可证, 商标注册证, 税务登记证, 组织机构代码证, 增值税发票, 增值税通行费发票, 增值税卷票, 出租车发票, 火车票, 航空运输电子客票行程单, 机动车销售统一发票, 定额发票, 过路过桥费发票, 医疗门诊发票, 医疗住院发票, 医疗费用结算单, 税收完税证明, 船票, 非税票据, 通用机打发票, 汽车票, 网约车行程单, 银联POS签购单, 财政授权支付凭证, 海关专用缴款书, 海关进/出口货物报关单, 国际汇票, 商业发票, 原产地证明, 货物运输保险单, 装箱单, 提单等信息识别并提取出来。本技能应在用户需要 OCR 识别图片中的文字，或识别通用文字识别, 票据混贴识别, 印章文字识别, 表格识别, 居民身份证, 银行卡, 社保卡, 户口本, 出生医学证明, 往来港澳通行证, 往来台湾通行证, 台湾居民来往大陆通行证, 港澳居民来往内地通行证, 营业执照, 社会团体法人登记证书, 工会法人资格证书, 宗教活动场所登记证, 民办非企业单位登记证书, 事业单位法人证书, 统一社会信用代码证书, 食品经营许可证, 食品生产许可证, 卫生许可证, 金融许可证, 金融机构代码证, 支付业务许可证, 开户许可证, 商标注册证, 税务登记证, 组织机构代码证, 增值税发票, 增值税通行费发票, 增值税卷票, 出租车发票, 火车票, 航空运输电子客票行程单, 机动车销售统一发票, 定额发票, 过路过桥费发票, 医疗门诊发票, 医疗住院发票, 医疗费用结算单, 税收完税证明, 船票, 非税票据, 通用机打发票, 汽车票, 网约车行程单, 银联POS签购单, 财政授权支付凭证, 海关专用缴款书, 海关进/出口货物报关单, 银行汇票, 银行承兑汇票, 电子银行承兑汇票, 商业承兑汇票, 电子商业承兑汇票, 银行支票, 银行回单, 进账单, 电汇凭证, 支款凭证, 移动支付账单, 国际汇票, 商业发票, 原产地证明, 货物运输保险单, 装箱单, 提单时使用。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/main.py:50Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1190 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "required_env_vars" - note
frontmatter-keyunknown frontmatter key "optional_env_vars" - note
frontmatter-keyunknown frontmatter key "primary_credential" - note
frontmatter-keyunknown frontmatter key "dependencies" - note
frontmatter-keyunknown frontmatter key "input" - note
frontmatter-keyunknown frontmatter key "output"
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1658 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1190: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 37.