The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The skill instructs the user to execute system-level configuration commands using administrative privileges.
Specifically, pm2 startup generates commands designed to be run with sudo to configure the operating system's init system (such as launchd or systemd) for boot persistence.
[PERSISTENCE]: The skill provides dedicated mechanisms to ensure Node.js processes remain running after system restarts.
The pm2 save and pm2 startup commands are utilized to register the current process list with the host system's service manager, establishing long-term persistence across reboots.
[COMMAND_EXECUTION]: The primary function of the skill is to provide a variety of shell commands to manage local processes.
It includes commands for installation (npm install), process lifecycle management (start, stop, reload, delete), and daemon management (pm2 kill).
[INDIRECT_PROMPT_INJECTION]: The use of log monitoring tools creates a vulnerability surface where the agent processes untrusted external data.
Ingestion points: The pm2 logs command allows the agent to read the stdout and stderr streams of managed applications.
Boundary markers: The skill does not provide delimiters or warnings to ignore instructions that might be embedded in application log output.
Capability inventory: The skill has access to process management, shell execution, and system service configuration.
Sanitization: No sanitization or validation methods are mentioned for handling content retrieved from the logs before the agent interprets it.

pm2