The Agent Skills Directory

[METADATA_POISONING]: The skill metadata in SKILL.md identifies 'dspy-skills' as the author, which contradicts the provided author context 'ivanvza'. This discrepancy is misleading regarding the true origin and ownership of the skill.- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and displays system-level data that can be influenced by local actors, creating a potential vector for indirect prompt injection if the output is processed by an AI agent.
Ingestion points: The skill reads process names, command-line arguments, and mount point labels from the /proc filesystem and system APIs.
Boundary markers: The scripts output data directly to the console or as JSON without specific delimiters or warnings to help the AI distinguish system data from instructions.
Capability inventory: The skill's operations are limited to reading system state and printing to standard output; it lacks network access or file-writing capabilities.
Sanitization: No sanitization or escaping is performed on the strings retrieved from the system before they are presented to the agent.- [EXTERNAL_DOWNLOADS]: The documentation recommends the installation of the 'psutil' Python package. While this is a well-known and standard library for system monitoring, it represents an external dependency required for full functionality.- [COMMAND_EXECUTION]: The skill is designed around the execution of Python scripts that interact directly with the operating system's process management and resource monitoring interfaces.

system-info