superpowers

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of markdown documentation, pseudo-code examples, and high-level process descriptions. There are no executable scripts (e.g., .sh, .py, .js) or automated commands.
  • PROMPT_INJECTION (SAFE): The instructions provide a methodology for task management and coding (e.g., 'Plan then execute') rather than attempting to override the agent's core safety protocols or system instructions.
  • DATA_EXFILTRATION (SAFE): There are no network calls, credential placeholders, or commands that interact with the file system or sensitive data.
  • INDIRECT PROMPT INJECTION (SAFE): While the skill describes a workflow for reviewing user-provided code (diffs), it does not include tools or executable capabilities that could be subverted by malicious input within those diffs.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:31 AM