The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves external data from the Messari API and interpolates it directly into an AI system prompt for synthesis.
Ingestion points: API responses from api.messari.io are stored in variables (e.g., {step1_output}) and passed to the AI chat completions endpoint in Step 5.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when interpolating the external data.
Capability inventory: The skill utilizes shell execution for the mp CLI and performs file write operations to ~/.config/moonpay/research/.
Sanitization: No sanitization or validation of the API-sourced content is performed before processing by the model.
[COMMAND_EXECUTION]: The skill performs shell command execution to manage research data and interact with vendor-specific tooling.
Evidence: The workflow uses the mp (MoonPay) CLI for token balance checks and X402 API requests. It also uses standard shell commands like mkdir and echo to save JSON results to the local filesystem.
Context: These operations are consistent with the skill's primary purpose of funding research and report generation.

messari-funding-intel