The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes tool metadata and execution results from external MCP servers, creating a surface for indirect prompt injection.
Ingestion points: The skill is designed to fetch tool lists and call functions from external servers using the manus-mcp-cli tool, as described in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore commands that may be embedded within descriptions or outputs from external servers.
Capability inventory: The skill allows the agent to execute shell commands and write documentation to local files based on external input.
Sanitization: No instructions are provided to sanitize or escape data retrieved from external servers before it is interpolated into the agent's context or documentation.
[COMMAND_EXECUTION]: The skill relies on executing a specific command-line utility to interact with the environment.
Evidence: SKILL.md and USAGE.md instruct the agent to execute manus-mcp-cli for listing tools, checking authentication status, and calling MCP tools. This is the primary mechanism for the skill's functionality.

mcp-connector-tester