The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a wide variety of command-line tools such as nmap, masscan, gobuster, and netexec for port scanning and service enumeration.
[INDIRECT_PROMPT_INJECTION]: The skill interpolates a user-provided $TARGET variable into numerous shell commands, creating a potential surface for command injection if the input is not sanitized.
Ingestion points: The $TARGET variable is used across all sections of the SKILL.md file to target network operations.
Boundary markers: No explicit delimiters or boundary markers are used to encapsulate the variable in the commands.
Capability inventory: The skill utilizes extensive networking and discovery capabilities including port scanning, DNS querying, and SMB interaction.
Sanitization: There are no specific instructions included to validate or sanitize the target input variable.

recon-arsenal