Security audit
Security checks for vulnerabilities and agentic risk
This skill transparently pushes the agent to troubleshoot more thoroughly, with no executable code or hidden persistence, though it may make the agent more forceful automatically.
Install this if you want the agent to be more persistent and evidence-driven when stuck. Because implicit invocation is enabled, it may apply this assertive troubleshooting style without an explicit $pua call, so keep normal tool approvals and boundaries in place if file reads or command execution matter in your workspace.
The file is entirely written as a Chinese-only skill and does not offer any language choice, opt-in, or justification for restricting output to this locale. Under the policy for natural-language violations, a skill that forces a specific language without user choice should be flagged.
The skill enables implicit invocation while describing its use case in very broad behavioral terms like pushing through stuck tasks and being more exhaustive. That can cause the agent to auto-apply this high-pressure behavior in unrelated contexts, overriding normal caution and increasing the chance of unsafe persistence, reduced deference to user intent, or bypass of safer stopping conditions.
