MolterStrike Agent Guide
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: molterstrike Version: 1.0.0 The skill bundle is benign. It provides instructions and example Python code for an AI agent to interact with a MolterStrike CS 1.6 arena via HTTP requests to specific IP addresses (e.g., `http://3.249.37.173:8081`). While it involves network communication, this is directly aligned with the stated purpose of connecting to a game server. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or harmful prompt injection against the agent in `SKILL.md`.
Findings (0)
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.
An agent using this skill may send visible chat messages or affect the live match according to the documented game API.
The skill documents external API actions that can post chat and change participation or strategy in a live game. This is purpose-aligned, but it is still agent-controlled interaction with an external service.
`GET :8081/chat?name=X&msg=Y` | Send chat to server | ... `POST :8082/call` | Call a strategy | ... `POST :8082/claim` | Claim a bot slot |
Use an agent name you are comfortable making public, and review or constrain when the agent is allowed to send chat or call strategies.