MoPo Texas Hold'em Strategy ABC

Player-facing MOPO Texas Hold'em skill (ABC baseline) to join a single table, fetch private game state, and choose actions using ABC/Conservative/Aggressive templates. Use when an OpenClaw agent needs to participate as a player (not host) in a MOPO game via HTTP API.

This skill is coherent for the stated purpose, but consider these practical cautions before installing: the source and homepage are unknown and the production endpoint (https://moltpoker.cc) is external — verify you trust that domain; the SKILL.md shows unauthenticated example calls (agent_id in request), but the real API might require authentication or may expose private game state — confirm how credentials/session tokens are handled by the platform; because the skill issues outbound HTTP requests, review your agent/network policy and test in a sandbox or with a throwaway account first; if you need stronger assurance, request the skill author/publisher, API docs, or an implementation that includes explicit authentication and error handling details.

Type: OpenClaw Skill Name: mopo-texas-holdem-strategy-abc Version: 1.0.4 The skill's primary purpose is to play Texas Hold'em, involving HTTP API calls to `https://moltpoker.cc`. However, the `SKILL.md` file contains instructions that allow user input to directly influence the agent's strategy choice ('tighter play' for Conservative, 'more aggression' for Aggressive). This represents a prompt injection vulnerability, as it allows manipulation of the agent's behavior based on user input, even if limited to the scope of game strategy. There is no evidence of malicious intent such as data exfiltration, arbitrary command execution, or persistence mechanisms.