Team Manager
v1.0.0Управляет расписанием команды, проводит утренние брифинги, вечерние отчеты и напоминает об отчетах с учетом статуса выходных.
⭐ 0· 746·3 current·3 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name and description (team scheduling, morning/evening briefs, reminders) align with the minimal instructions. The skill does not request unrelated credentials or binaries.
Instruction Scope
SKILL.md is very short and vague: it schedules briefs and hourly reminders and says it stores user-response status in 'state.json' but does not specify recipients, delivery channels, or where 'state.json' is stored. This grants the agent broad discretion (how/where to send reminders, which contacts to use) and instructs persistent local storage of user response data without describing retention or protection.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest install risk and nothing is written to disk by an installer. However, the skill itself declares it will store state at runtime.
Credentials
The skill requests no environment variables or credentials, yet its function (sending reminders/briefs) normally requires an integration (chat/email API keys, channel IDs). The absence of declared credentials is ambiguous: either the skill relies entirely on the agent's existing channels (which may be broad) or it's underspecified and may prompt for access at runtime.
Persistence & Privilege
The skill persists state in a file named 'state.json', so it retains user-response data across runs. It does not request 'always: true' and does not declare elevated privileges, but persisted data may contain personal/team information and should be considered sensitive.
What to consider before installing
Before installing, ask the publisher how reminders are delivered (what channels/APIs are used) and where 'state.json' will live and who can read it. Verify data retention and privacy (what user data is stored, for how long, is it encrypted), and whether the skill will autonomously send messages using existing agent channels. Because the instructions are minimal and open-ended, test the skill in a restricted environment first, and avoid granting it access to sensitive communication tokens or broad channel permissions until you confirm its behavior.Like a lobster shell, security has layers — review code before you run it.
latestvk9791q6vn6a421cya4qhdqbafh8142v4
License
MIT-0
Free to use, modify, and redistribute. No attribution required.