The Agent Skills Directory

[SAFE]: The skill consists solely of markdown instructions and reference files aimed at providing copywriting guidance. There is no evidence of command execution, network activity, or obfuscation.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read a local context file (.claude/product-marketing-context.md) if it exists. While this represents an ingestion point for untrusted data, it is a standard and intended feature for providing the agent with project-specific context. The skill lacks dangerous capabilities (like network exfiltration or shell access) that would allow this surface to be weaponized effectively, and the risk is considered negligible within the intended use case.
[NO_CODE]: The skill does not include any scripts, executables, or dynamic code generation components, significantly reducing its attack surface.

copywriting