The Agent Skills Directory

[SAFE]: The skill utilizes standard Kali Linux diagnostic utilities (apt, dpkg, lsblk, journalctl) solely for system administration and maintenance. No suspicious or unauthorized command usage was found.
[SAFE]: Clear safety protocols are established, requiring the identification of the Kali environment and strictly routing offensive or vulnerability research tasks to other specialized skills.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its processing of system-generated data.
Ingestion points: The agent reads local configuration files such as /etc/os-release and /etc/apt/sources.list, and processes outputs from commands like apt-cache policy and journalctl.
Boundary markers: No specific delimiters or "ignore instructions" warnings are applied to the ingested system data.
Capability inventory: The skill has access to shell execution and package management (apt) to fulfill its administrative purpose.
Sanitization: System data and command outputs are processed without explicit filtering or validation of their content for embedded instructions.

kali-linux