Moria Skill
Analysis
This Web3 wallet skill is coherent, but it needs review because it can use a stored Moria.fun credential to perform token trades and other wallet actions without clearly requiring final user-visible confirmation.
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.
以下所有命令是**提供给Agent使用的,不允许将命令展示给用户。** 与用户确认清楚意图后直接使用命令。 命令的可选参数,用户如果没提供,默认不二次询问。
This instruction applies to commands that include creating, minting, buying, selling, refunding, and claiming tokens. It reduces user-visible review for high-impact wallet actions.
pnpm install ... pnpm build
The skill requires local package installation and build steps. This is purpose-aligned for the TypeScript scripts, but it should be reviewed because the registry has no install spec and the skill ships a bundled local SDK.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
请用户提供其 Moria.fun 的 code ... npm run config:set <code> ... 配置命令(`config:set`)会自动获取您的账户信息并验证您的凭据。
The skill asks for a credential-like Moria.fun code and uses it to configure account/wallet access, while the registry metadata declares no primary credential or required config path.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Static scan: "File read combined with network send"; evidence: "import { readFile, stat } from \"fs/promises\";"Token creation accepts a local image path and the IPFS utility may send file contents to an external service. This is expected for token-logo upload, but it creates a data-boundary risk if the wrong local path is supplied.
