The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill connects to the official Openfort API at https://www.openfort.io/api/mcp to retrieve documentation and metadata for its source code repositories.
[COMMAND_EXECUTION]: The skill exposes the openfort command-line interface as a local MCP server, providing the agent with tools to manage accounts and execute on-chain transactions.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads external documentation and code which then informs the agent's use of powerful CLI tools.
Ingestion points: External data enters the context via the mcp__openfort-docs__read_page and mcp__openfort-docs__read_source_file tools.
Boundary markers: No specific delimiters or instructions to ignore embedded content are defined in the skill documentation.
Capability inventory: The agent can perform sensitive blockchain operations using the @openfort/cli suite.
Sanitization: The skill does not implement explicit validation or sanitization for the content retrieved from external sources.

openfort