The Agent Skills Directory

[SAFE]: The skill is composed exclusively of markdown files providing writing instructions and frameworks. No executable scripts, binaries, or active code components are present.
[NO_CODE]: Analysis confirms the absence of Python or Node.js logic, which significantly reduces the attack surface for most technical threat categories.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation techniques was found within the instructions or metadata.
[SAFE]: The skill references a local file for product context (.claude/product-marketing-context.md), which is a standard method for agents to maintain state. As the skill lacks network and system-level capabilities, this does not present a data exfiltration risk.

copywriting