The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions include numerous shell commands for network discovery, port scanning, and vulnerability assessment using tools like Nmap, Masscan, and Nikto in references/detailed-guide.md.- [PRIVILEGE_ESCALATION]: The guide uses sudo for administrative tasks such as starting services (systemctl), installing system packages (apt), and configuring network interfaces for wireless monitoring (airmon-ng) as seen in references/detailed-guide.md.- [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface where the agent processes untrusted data from external targets via scan results.
Ingestion points: Data enters the context through files like nmap_scan.xml during import or report generation steps in references/detailed-guide.md.
Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded content within the scan results.
Capability inventory: The skill has extensive command execution capabilities (Nmap, Burp, Metasploit, etc.) as detailed in references/detailed-guide.md.
Sanitization: Absent; the instructions do not specify sanitization or validation of the ingested scan data.- [EXTERNAL_DOWNLOADS]: The skill references standard package managers and registries to install security tools.
Fetches prowler and scoutsuite from PyPI using pip.
Installs openvas from the official repository using apt.
Uses the official owasp/zap2docker-stable image from Docker Hub.

scanning-tools