skills/openclaw/clawdinators/fleet/Gen Agent Trust Hub

fleet

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script at /var/lib/clawd/repos/clawdinators/scripts/fleet-control.sh to perform deployment and status actions.
  • The script is called with user-influenced arguments <action> and [target].
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied parameters to interact with the fleet control script, creating an injection surface.
  • Ingestion points: User input for fleet management commands (action and target) in SKILL.md.
  • Boundary markers: None; user input is interpolated directly into the script execution command without delimiters.
  • Capability inventory: Execution of a shell script with the ability to modify fleet state (deploy/rollback).
  • Sanitization: No validation or escaping is specified for the input parameters before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 11:38 AM