skills/seabbs/skills/setup-scripts/Gen Agent Trust Hub

setup-scripts

Warn

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to generate shell scripts in the user directory and perform a 'smoke test' by executing them. It specifically instructs the use of 'chmod +x' to make these dynamically created files executable, which is a risk for executing arbitrary local code.
  • [PROMPT_INJECTION]: The 'Auto-Exit' section contains a directive marked as 'IMPORTANT' that instructs the agent to 'automatically exit' after completion. This is an attempt to override the agent's standard interaction lifecycle and safety reporting protocols.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 07:16 AM