The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script (scripts/connector-status.py) to retrieve status information about various connectors.
[DATA_EXFILTRATION]: The skill processes the .mcp.json configuration file and system environment variables. These sources are known to store sensitive information, including API keys and authentication credentials for MCP integrations.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests data from external files and environment variables that are then used as context for the agent's response.
Ingestion points: Reads from .mcp.json and system environment variables.
Boundary markers: The instructions do not specify the use of delimiters or ignore-instructions for the data retrieved from these sources.
Capability inventory: The skill has the ability to execute shell commands via python3 subprocesses.
Sanitization: There is no mention of sanitizing or validating the contents of the configuration files before they are processed.

integrations