pua
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses strong language metaphors (PUA/Pressure) to define a highly compliant persona. It instructs the agent to accept criticism without defense and follow a specific apology loop. These instructions are within the scope of role-play behavior and do not attempt to bypass core safety guardrails, extract system prompts, or disable model safety filters.
- [NO_CODE]: The skill consists exclusively of markdown documentation and YAML frontmatter. It lacks any scripts (Python, JavaScript, Shell) or configurations that interact with the file system, network, or external APIs, thereby posing no technical risk of execution or data exfiltration.
Audit Metadata