The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the t2000 pay command to perform HTTP requests and authorize USDC payments on the Sui blockchain. This allows the agent to interact with external financial systems and network endpoints.- [EXTERNAL_DOWNLOADS]: The skill documentation requires the presence of the @t2000/cli and @t2000/x402 packages, which are fetched from the NPM registry.- [REMOTE_CODE_EXECUTION]: The skill instructs the setup of its environment using npx @t2000/cli init, a command that downloads and executes remote code from a public registry.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes and returns responses from arbitrary external API endpoints.
Ingestion points: The skill ingests untrusted data from the HTTP response body of URLs provided to the t2000 pay command.
Boundary markers: There are no defined delimiters or instructions to treat the API response as untrusted data or to ignore instructions contained within it.
Capability inventory: The skill provides the agent with capabilities to execute shell commands (t2000), perform network requests, and broadcast blockchain transactions.
Sanitization: No sanitization, validation, or escaping of the API response content is performed before it is presented to the agent's context.

t2000-pay