using-superpowers
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses forceful instructional language to ensure the agent follows a specific workflow for skill discovery and usage. While it contains directives to override default system behavior, it includes an explicit instruction priority that places user-provided instructions as the highest priority.
- [COMMAND_EXECUTION]: The skill includes documentation for mapping platform-neutral tool calls (e.g., Task, Skill, Bash) to their platform-specific equivalents in environments like Copilot CLI and Gemini CLI. These references are provided as cross-platform guidance for the agent.
Audit Metadata