assumption-buster
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local shell script (scripts/bust.sh) used to generate analysis templates based on user-provided assumptions. It also references npm commands in its documentation for execution examples. This behavior is consistent with the skill's intended use as a development and architectural tool.
- [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized network access was found. The adversarial language used ('Think like an attacker', 'Aggressively challenge') is contextually appropriate for the skill's stated purpose of stress-testing beliefs and identifies no attempts to bypass safety guardrails.
Audit Metadata