KibiBot
Security checks across static analysis, malware telemetry, and agentic risk
Overview
KibiBot is a coherent Kibi integration, but it asks for a Kibi API key that can enable on-chain token creation and automatic credit reloads from a trading wallet without clearly shown limits or confirmations.
Review this skill before installing. If you use it, create a limited Kibi API key, avoid enabling Agent Reload unless you have clear spending limits, require confirmation before token creation or credit reloads, and verify the GitHub source or use a pinned version. Only route sensitive prompts through the Kibi LLM Gateway if you are comfortable with KibiBot processing and billing those requests.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A mistaken or overbroad agent action could create public on-chain assets or move value from a trading wallet into Kibi Credits.
The skill declares high-impact actions involving on-chain token creation and automatic wallet-funded credit reloads, but the provided text does not show clear limits, transaction confirmations, or spending controls.
description: Create tokens on-chain, check fee earnings, check Kibi Credit balance, trigger agent credit reload... Enable **Agent Reload** if you want the agent to top up your Kibi Credits automatically from your trading wallet.
Use only with explicit user confirmation for token creation and reloads; enable Agent Reload only if you understand the wallet source, spending limits, and how to revoke the permission.
A broadly permissioned Kibi key could let the agent spend credits or trigger reload-related account actions beyond what the user expected.
The API key can carry multiple permissions, including LLM billing and automatic credit reload. The registry metadata lists no primary credential, so the privilege boundary is under-declared at the registry level.
**Auth:** API key required — get yours at [kibi.bot/settings/api-keys]... **Permissions:** Base API is always included. Enable **Kibi LLM Gateway**... Enable **Agent Reload**...
Create a least-privileged Kibi API key, enable only the permissions needed, avoid enabling Agent Reload by default, and revoke or rotate the key after sensitive use.
Conversation content sent to the configured models may pass through KibiBot's LLM gateway and consume Kibi Credits.
The optional LLM Gateway routes model requests through KibiBot. This is disclosed and purpose-aligned, but it affects where prompts, files, and conversation context may be sent and billed.
This step registers KibiBot as your agent's AI model provider... point your `base_url` to `https://llm.kibi.bot/v1` with your `kb_...` API key
Review KibiBot's privacy and billing terms before routing sensitive prompts or proprietary data through the gateway.
If the referenced repository changes, a later install could differ from what was reviewed.
The install reference points to a GitHub branch path rather than a pinned release or commit. No code files were included in this scan, so the exact external install contents are not verified here.
**Install:** `install the kibibot skill from https://github.com/KibiAgent/skills/tree/main/kibibot`
Install from a pinned commit or reviewed release, and inspect the repository before granting API keys or wallet-related permissions.