Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Nimmit Onboarding
v1.0.0Use when a new user messages the bot for the first time or sends /start. Guides them through conversational onboarding — organization setup, industry, langua...
⭐ 0· 47·0 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 stated purpose (conversational onboarding via Telegram) aligns with creating org/profile files (IDENTITY.md, TASKS.md) and scheduling briefings. However, instructions to 'install the matching skill pack(s)' and to use exec/copy to manipulate skill packs are more powerful than a simple chat flow and should be justified by the author (where do skill packs come from, which ones, from what source?).
Instruction Scope
SKILL.md explicitly instructs the agent to use write to update workspace files, use exec to copy/install skill packs, and use cron to schedule daily briefings. These actions read and modify persistent workspace state and system scheduling. The instructions do not constrain the source of skill packs, do not require explicit user consent for installation, and say to perform setup 'silently' (no technical details to user), which increases risk of unreviewed changes.
Install Mechanism
There is no install spec in the registry, but the runtime instructions tell the agent to install/copy skill packs via exec. Because provenance and installation steps are unspecified, this could lead to installing arbitrary code or untrusted packages. The manifest gives no safe source or verification for any install.
Credentials
The skill requests no environment variables, credentials, or external config paths in the manifest. It operates on workspace files (IDENTITY.md, SOUL.md, etc.), which is proportionate to onboarding. No unrelated secrets are requested.
Persistence & Privilege
Although always:false and user-invocable:true (good), the skill instructs creating a cron job to send daily briefings and to install skill packs, which grants it persistent behavior and ongoing side effects. The skill would modify system scheduling and workspace contents without details on approvals or rollback.
What to consider before installing
This skill appears to do what it says (conversational onboarding) but its runtime steps will modify your workspace and system (write files, copy/install 'skill packs', and create a cron job) without specifying where those skill packs come from or asking for explicit consent. Before installing or enabling this skill: 1) Ask the publisher to list exactly which skill packs will be installed and their sources (URLs, registry names, or repository release tags). 2) Require that installs perform cryptographic verification or come from a trusted registry. 3) Restrict or review any exec/copy operations and cron changes in a sandbox environment first. 4) Ensure you have an allowlist for which users can trigger onboarding and a way to review/rollback changes to IDENTITY.md, SOUL.md, HEARTBEAT.md, TASKS.md and crontab. 5) If you cannot verify the provenance of skill packs or want tighter control, do not enable automated installation/scheduling and require manual approval for setup steps. If you want more certainty, ask the skill author for an explicit install plan or provide the list of skill packs here for review.Like a lobster shell, security has layers — review code before you run it.
latestvk977qpnbbjnh7n5hqb1sr5549d84ceaw
License
MIT-0
Free to use, modify, and redistribute. No attribution required.