The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute a wide variety of powerful security tools, such as sqlmap, hydra, nuclei, and feroxbuster. While these are intended for authorized security engagements, they represent high-capability tools that perform active network probes and automated attacks.
[INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent processes and interprets data from external web targets, which can be manipulated by an adversary to influence the agent's behavior.
Ingestion points: External target URLs, HTTP response headers, rendered JavaScript content, and the output of various automated scanners (e.g., nuclei, whatweb).
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded in the retrieved web content.
Capability inventory: The skill possesses extensive network capabilities (HTTP requests, database exploitation, authentication brute-forcing) and the ability to interact with local configuration files (e.g., /etc/hosts).
Sanitization: There are no instructions for sanitizing or escaping the data retrieved from external targets before it is processed by the agent or used in subsequent commands.

web-arsenal