using-superpowers

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional Markdown files intended to guide agent behavior and contains no malicious logic.
  • [NO_CODE]: No executable scripts or binary files are included in the skill; all logic is provided via natural language instructions and tool-mapping documentation.
  • [PROMPT_INJECTION]: The skill uses imperative language (e.g., 'ABSOLUTELY MUST', 'not negotiable') to enforce a workflow, but it mitigates risks by explicitly stating that user instructions always take precedence over the skill's directives.
  • [COMMAND_EXECUTION]: Tools such as Bash and shell commands are referenced only for the purpose of documenting platform-specific tool equivalents and are not invoked with malicious parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 12:09 PM