Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Expense Invoice Ocr
v0.1.0支持识别企业财务报销场景的常见票据，包括增值税专用发票、增值税普通发票、增值税卷票、增值税电子发票、出租车发票、火车票、铁路电子客票、航空运输电子客票行程单、机动车销售统一发票。
⭐ 0· 71·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The skill implements invoice/ID OCR by calling Sugon-Scnet's API, which is coherent with the name and description. However the registry metadata at the top of the report claims "Required env vars: none" and "Primary credential: none" while the code and SKILL.md require SCNET_API_KEY — an inconsistency in declared requirements.
Instruction Scope
SKILL.md and scripts/main.py clearly instruct the agent to read a local file path and POST the file to https://api.scnet.cn/api/llm/v1/ocr/recognize with Authorization: Bearer <SCNET_API_KEY>. That is expected for an external OCR service, but it means user images (which may contain sensitive personal/financial data) are transmitted to a third-party endpoint; the documentation does not provide a privacy/retention statement.
Install Mechanism
There is no install script or external download. This is an instruction+script-only skill included in the bundle. It imports the requests library (not installed by the skill itself), so runtime environment must provide that dependency.
Credentials
The code and SKILL.md require an SCNET_API_KEY (and config/.env) and config.json lists environment_variables ["SCNET_API_KEY"] and permissions ["network","filesystem"]. Yet the top-level registry metadata shows no required env vars and no primary credential. The missing/mismatched metadata is a red flag: the skill does need a secret API key and network access to function, and that requirement should be declared up-front.
Persistence & Privilege
always:false and no special persistence or modification of other skills. The skill requests network and filesystem access (in config.json) which is appropriate for its function; note that autonomous invocation (the platform default) combined with network access and a stored API key increases the impact if the skill is misused.
What to consider before installing
What to check before installing or using this skill:
- Confirm the SCNET_API_KEY requirement: the code and docs require you to create config/.env with SCNET_API_KEY, but the registry metadata omitted this — verify the credential is legitimate before providing it.
- Understand privacy: using the skill uploads your files (invoices, IDs, bank cards) to api.scnet.cn. Do not send sensitive images unless you trust the service and its data handling/retention policy.
- Protect the API key: treat SCNET_API_KEY like a secret (do not paste it into untrusted UIs). Revoke it if you suspect compromise.
- Runtime deps: the script uses the requests library; ensure your environment provides it.
- If you need offline/local-only OCR for sensitive documents, prefer a skill that runs models locally or declare that no external network is used.
- Because the metadata is inconsistent, prefer to review the bundle code (scripts/main.py and SKILL.md) yourself or ask the author to fix the manifest before granting broad access.Like a lobster shell, security has layers — review code before you run it.
latestvk97dyc31yh1jvqzd455g28gned83papz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.