The Agent Skills Directory

[SAFE]: The skill consists entirely of high-level instructions for an AI agent to perform risk analysis, prioritizing safety, correctness, and operational clarity. It does not include any commands, scripts, or network operations.
[SAFE]: No evidence of credential exposure, data exfiltration, or persistence mechanisms was found. The instructions focus on mapping workflows and identifying technical/financial risks within a provided context.
[SAFE]: No obfuscation, prompt injection, or dynamic code execution patterns are present. The metadata specifies a read-only sandbox mode, which is a restrictive and safe configuration.

risk-manager