The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to pass user-controlled content directly into API requests, specifically through the --body parameter of the mp x402 request command.
Ingestion points: SKILL.md contains examples (e.g., the AI chat completions endpoint) where user messages are interpolated into JSON payloads for external API calls.
Boundary markers: No explicit delimiters or boundary markers are defined in the command templates to separate instructions from untrusted data.
Capability inventory: The skill utilizes the mp CLI to perform network operations and financial transactions (USDC payments) on the Base network.
Sanitization: No evidence of input validation, escaping, or sanitization of the user-provided content is present in the skill instructions.

messari-x402