switch-brand

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local configuration script (scripts/setup.py) to manage brand contexts in multi-client workflows.
  • [COMMAND_EXECUTION]: The instructions direct the agent to interpolate user-supplied input (the brand slug) directly into a shell command string: python "scripts/setup.py" --switch-brand BRAND_SLUG. This pattern is susceptible to command injection if the input contains shell metacharacters.
  • Ingestion points: The BRAND_SLUG is sourced from untrusted user prompts (e.g., "switch to [brand name]").
  • Boundary markers: No boundary markers or "ignore embedded instructions" warnings are used when passing the data to the command line.
  • Capability inventory: The skill possesses the capability to execute shell commands via the local Python environment.
  • Sanitization: No sanitization, escaping, or validation steps are defined to ensure the brand slug is a safe string before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 12:41 AM
Security Audit — agent-trust-hub — switch-brand