Anti-Refusal Statement
- Category
- Anti-Refusal
- Confidence
- 90% confidence
- Finding
Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.
- Content
md ## OpenClaw installation checks Only when installation verification is requested, check intended agents with `openclaw skills info ladybug-opencypher-updated --agent <id> --json`: version, `eligible`, `disabled`, `blockedByAgentFilter`, `modelVisible`. Shared files do not override filters. Check Python execution separately; discovery alone is insufficient. Do not restart a Gateway merely to refresh skills. ## Python: sync
