messagemanager

v1.0.0

汇总企业微信群聊/单聊消息,提取重点、待办、风险与决策,输出可读的日报/周报/会议纪要;当用户提到“企业微信消息总结、群聊总结、提取待办、生成周报”等需求时触发。

0· 87·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name, description and workflow all describe summarizing Enterprise WeChat (群聊/单聊) messages into structured reports; nothing in the metadata asks for unrelated capabilities or credentials.
Instruction Scope
SKILL.md restricts itself to processing provided chat text or screenshots and describes a clear, bounded pipeline (cleaning, clustering, extraction, todo/risk identification, templated output). It mentions screenshots require OCR but does not prescribe an OCR service or instructions for image handling — this is not incoherent but means the agent/operator must decide how to perform OCR and how images are provided. Also: the skill will process potentially sensitive enterprise messages, so data handling/retention and whether OCR is done locally vs. via external services are important operational considerations.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk and no external packages or downloads are requested.
Credentials
No environment variables, credentials, or config paths are requested. The lack of required secrets is proportional to the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skills. Autonomous invocation is allowed by default but is not combined with other concerning privileges.
Assessment
This skill appears coherent and safe in terms of requested permissions (it asks for no credentials or installs). Before installing/using it, consider: (1) Do not paste or upload highly sensitive secrets or regulatory-protected data unless you trust where processing/OCR happens; redact if needed. (2) Decide whether OCR will be done locally or via an external service — if external, check that service's privacy/retention. (3) Confirm your organization’s policy for sharing chat logs with third-party tools. (4) If you need the agent to process images, supply pre-OCR text or an approved OCR tool to avoid unexpected network calls. If you can get answers to those operational questions, this skill's behavior matches its description.

Like a lobster shell, security has layers — review code before you run it.

latestvk97486sr6wgkbm60q4yf6yzjkx83j6b8

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments