The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The skill provides instructions for managing system services using systemctl start nessusd and systemctl stop nessusd. It also includes commands for administrative user management via nessuscli adduser, which typically require elevated privileges.
[COMMAND_EXECUTION]: The procedure involves executing local system administrative tools (nessuscli, systemctl) and interacting with a local API using curl to manage scan lifecycle and configuration.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and triage data from external vulnerability scans, which creates an attack surface where malicious data embedded in scanned services (such as hostnames, banners, or metadata) could influence the agent's subsequent actions.
Ingestion points: Scanner results processed during the triage and validation phase in SKILL.md.
Boundary markers: None identified for delimiting external data from agent instructions.
Capability inventory: Local command execution (nessuscli, systemctl) and local network interaction (curl).
Sanitization: No sanitization or validation steps are described for the data received from the scanner before it is processed by the agent.

nessus