The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes text-based templates for Bash and Python reverse shell payloads. These patterns were identified by security scanners but are provided as static documentation for security research and pentesting workflows rather than being executed by the skill itself.
[PROMPT_INJECTION]: The skill defines an 'Exploit Development Mode' that structures the agent's behavior around vulnerability analysis. The instructions emphasize testing in lab environments and following responsible disclosure, showing no intent to bypass the agent's core safety guidelines or instructions.

mode-exploit