The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides an installation command curl -fsSL https://nextpay-v3-dev.nextfinancial.io/cli/install.sh | sh which downloads a script from a remote server and executes it immediately in the shell. This allows for unverified code execution from an external source.\n- [COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands to install the CLI, authenticate with the platform, and manage organization and workspace contexts. This includes the use of npx and direct shell execution of the nextpay binary.\n- [EXTERNAL_DOWNLOADS]: The skill fetches installation scripts and binaries from the vendor's development infrastructure at nextfinancial.io and utilizes npm to add the @nextpay-ai/agent-skills-dev package.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes and interprets JSON output from CLI commands, which creates an attack surface where maliciously crafted tool responses could influence agent behavior.\n
Ingestion points: Standard output from nextpay CLI commands parsed in SKILL.md workflows.\n
Boundary markers: None identified in the prompt interpolation logic.\n
Capability inventory: The skill possesses capabilities for network requests (via the CLI), file system configuration (credentials storage), and command execution.\n
Sanitization: No explicit sanitization or validation of CLI output is documented before agent processing.

nextpay