superpowers-verification-before-completion
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not include executable code, network operations, or access to sensitive files. It focuses on enforcing a verification workflow to prevent hallucinations and ensure accuracy.- [PROMPT_INJECTION]: The skill uses imperative language and strong directives (e.g., 'The Iron Law', 'Non-negotiable') to modify agent behavior regarding status reporting. However, these instructions are aimed at improving truthfulness and do not attempt to bypass safety filters, extract system prompts, or disable security protocols.
Audit Metadata