Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Compliance Review
v1.0.0Automatically reviews compliance of client claim authorization letters using customized templates and pushes results to Feishu every 30 minutes.
⭐ 0· 331·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill purports to check authorization letters and push results to Feishu every 30 minutes — that matches the interval and Feishu push settings found in config.js. However, config.js includes a loginUrl and reviewPath (suggesting it will log into an external/internal task system) and references Feishu webhook/channel environment variables, while the registry metadata lists no required environment variables or credentials. The presence of a login endpoint is not explained by SKILL.md and is inconsistent with the declared requirements.
Instruction Scope
SKILL.md states the skill 'does not collect/store customer personal information' and describes narrowly-scoped checks (handwritten signature detection and document existence). The code (config.js) enables audit logging to './memory/compliance-audit.jsonl' with 90-day retention, which contradicts the 'no storage' claim. Also SKILL.md does not mention interacting with the loginUrl/reviewPath defined in config.js — that suggests the agent may access an external task system or internal admin UI not described in the instructions.
Install Mechanism
There is no install spec (instruction-only), but package.json and code files are included. Dependencies are internal-looking names (openclaw-schedule, openclaw-browser, openclaw-vision, openclaw-message) which are plausible for scheduled checks, web automation, vision/OCR, and messaging. No external download URLs are present in the files shown. Because code and npm deps exist but no install instructions are declared in metadata, it's unclear how/when dependencies will be installed — ask the publisher/platform how the runtime environment is prepared.
Credentials
config.js expects FEISHU_WEBHOOK and FEISHU_CHANNEL_ID via process.env, but the skill metadata declares no required environment variables or primary credential. The config also contains a loginUrl that will likely require credentials or session cookies to access tasks; yet no login credentials or config paths are declared. This mismatch means the skill may require undisclosed secrets to function, or it may attempt to operate against an endpoint without clear authorization handling.
Persistence & Privilege
The skill requests local persistence: saveAuditLog true, logPath './memory/compliance-audit.jsonl', retentionDays 90. That gives the skill the ability to accumulate audit records over months. Combined with the SKILL.md assertion of not storing personal data, this is a contradiction that should be resolved. The skill does not request elevated platform privileges (always:false), but local log storage is a notable persistence behavior.
What to consider before installing
This skill has plausible functionality, but several inconsistencies merit caution before installing: (1) config.js expects FEISHU_WEBHOOK and FEISHU_CHANNEL_ID but the registry lists no required env vars — confirm what credentials the skill needs and where they will be stored. (2) The code sets up local audit logging with 90-day retention despite SKILL.md claiming no data is stored — ask what exactly is logged (are there PII/claim details?) and whether logs are kept encrypted or accessible to others. (3) config.js includes a loginUrl/reviewPath which implies it will access an external/internal task system; request the index.js (runtime code) to verify how it authenticates and what data it reads/writes. (4) Verify with the publisher whether dependencies are trusted and how/when npm packages will be installed. If you require privacy guarantees, obtain the runtime code (index.js), a data-handling policy, and a list of required env vars/credentials before enabling this skill.Like a lobster shell, security has layers — review code before you run it.
latestvk97etryg79bc88sna6erb6gsc582dcf0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.