kata-set-profile

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill performs legitimate project configuration tasks within a local context.
  • [COMMAND_EXECUTION]: The skill uses standard shell commands (ls, cat) to interact with a local .planning/config.json file. These operations are scoped to the project directory and do not involve sensitive system paths.
  • [PROMPT_INJECTION]: The skill implements strict input validation for the profile argument against an explicit whitelist of allowed values ('quality', 'balanced', 'budget') before processing, which effectively mitigates risks associated with untrusted input injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 11:59 AM