The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides tools such as assess_payram_project that scan local codebase files, creating a surface where untrusted data (like malicious instructions hidden in code or comments) could be ingested into the agent's context.\n
Ingestion points: Local project files scanned by assess_payram_project as described in SKILL.md.\n
Boundary markers: None identified in the documentation to delimit project content from agent instructions.\n
Capability inventory: The skill provides capabilities for generating code snippets via generate_payment_sdk_snippet and scaffolding full applications via scaffold_payram_app.\n
Sanitization: No explicit sanitization or validation of the scanned project content is mentioned.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone the MCP server repository from the vendor's GitHub repository at https://github.com/payram/payram-mcp. This is a standard procedure for utilizing the vendor's provided tooling.\n- [COMMAND_EXECUTION]: The documentation provides instructions to execute shell commands for cloning the repository and installing dependencies using git clone and yarn install. These commands target the vendor's own infrastructure and are part of the intended setup process.

payram-crypto-payments