The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill accepts user input that is subsequently used to build and execute shell commands, creating a potential injection surface.
Ingestion points: The instructions prompt for user-supplied values including Server name, URL, transport type, and Auth credentials in SKILL.md.
Boundary markers: The skill does not employ delimiters or specific instructions to isolate these inputs from the command structure.
Capability inventory: The skill utilizes the Bash tool with curl capabilities as defined in the allowed-tools metadata.
Sanitization: There is no evidence of input validation, sanitization, or escaping of the user-provided strings before they are interpolated into the curl commands.

add-mcp