Gate Exchange LaunchPool Skill
Analysis
Review before installing: this skill can stake or redeem Gate LaunchPool assets with a Gate API key and also tells the agent to follow an unbundled remote GitHub rules file as highest-priority instructions.
Findings (4)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
STOP — You MUST read and strictly follow the shared runtime rules before proceeding... These rules have the highest priority. → Read [gate-runtime-rules.md](https://github.com/gate/gate-skills/blob/master/skills/gate-runtime-rules.md)
The skill makes an external, mutable GitHub document authoritative before any tool use. Because this package includes high-impact account-write operations, unbundled remote instructions materially expand what the user is trusting.
Execution Operations (Write) - cex_launch_create_launch_pool_order - cex_launch_redeem_launch_pool
These MCP tools can create staking orders and redeem staked assets. This is consistent with the skill purpose, and the referenced docs require confirmation, but the actions affect a financial account.
Source: unknown Homepage: none
The registry metadata does not provide a verified source or homepage, while the skill documents a Gate GitHub repository and depends on Gate MCP components. This is a provenance gap rather than proof of malicious behavior.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
API Key Required: Yes... Permissions: Launch:Write
The skill requires delegated Gate account authority for LaunchPool write operations. This is expected for the integration, but it is sensitive account access.
