The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the pulumi preview command to validate changes. This is a standard practice for infrastructure-as-code (IaC) development and is used here as a safety check rather than for malicious purposes.- [SAFE]: The skill promotes security best practices by explicitly requiring the preservation of assumeRole and cross-account configurations, which prevents accidental degradation of security postures during infrastructure updates.- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized remote code execution was found. The instructions are focused on maintaining the integrity of existing infrastructure code.

pulumi-modify-existing