The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for text transformation and content adaptation. It does not contain any executable code, scripts, or commands.
[DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized network operations were detected. The skill mentions 'x-api' as a related skill for publishing, which is a standard reference to external tool functionality.
[PROMPT_INJECTION]: The instructions are designed to guide the agent's creative output and do not contain patterns aimed at bypassing safety filters or overriding core system instructions.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing untrusted user data (e.g., articles, posts) to create adapted variants.
Ingestion points: User-provided 'Primary Version' of content in SKILL.md.
Boundary markers: Not present.
Capability inventory: Text transformation and reference to publishing tools like x-api (SKILL.md).
Sanitization: None observed, as the skill relies on the underlying LLM's standard processing of input text.

crosspost