The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the mcporter CLI which supports the execution of arbitrary shell commands through the --stdio flag, such as mcporter call --stdio "bun run ./server.ts".
[EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of the mcporter package from the official Node.js npm registry.
[DATA_EXFILTRATION]: The tool handles sensitive operations including authentication (mcporter auth) and configuration management (mcporter config), and it can perform network requests to arbitrary URLs provided in the tool arguments.
[PROMPT_INJECTION]: The skill facilitates interaction with external MCP servers; as it processes the output from these external tools, it presents a surface for indirect prompt injection where external data could potentially contain instructions aimed at the agent. This is a risk factor inherent to tool-use skills.
Ingestion points: Untrusted data enters the context via mcporter call responses from external servers.
Boundary markers: None identified in the provided documentation to delimit tool output from agent instructions.
Capability inventory: The skill has the ability to execute shell commands (--stdio), manage auth tokens, and perform network requests.
Sanitization: No specific sanitization or filtering of external tool output is documented.

mcporter