The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and configuration files. It does not include any executable scripts or binary files, posing no direct threat to the execution environment.
[NO_CODE]: Analysis confirms the absence of Python, Node.js, or shell scripts. The skill relies purely on the language model's internal reasoning capabilities guided by the provided markdown instructions.
[DATA_EXPOSURE]: The instructions include a dedicated 'Safety Boundary' section that explicitly directs the agent to minimize or redact sensitive context before escalating tasks to other tools or services, which is a security best practice for multi-agent workflows.

deliberative-analysis