The Agent Skills Directory

[SAFE]: The skill is entirely composed of Markdown instructions and a JSON configuration for testing. There are no executable scripts (Python, Node.js, Shell, etc.) provided in the skill package.
[SAFE]: No network operations, external data fetching, or remote code execution patterns were detected. The skill operates entirely within the LLM's instructional context.
[SAFE]: There are no attempts at prompt injection or bypassing safety guidelines. The instructions are purely focused on marketing methodology and diagnostic frameworks.
[SAFE]: No sensitive data access or exfiltration patterns were found. The skill does not interact with the filesystem, environment variables, or credentials.
[SAFE]: No obfuscation techniques, such as hidden characters or encoded strings, are present in the provided files.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided marketing scenarios (untrusted data), it lacks any dangerous capabilities (file writing, shell execution, network requests) that could be exploited through injection. The risk is negligible.

wom-diagnosis