The Agent Skills Directory

[SAFE]: No prompt injection or behavior override patterns detected; the instructions are strictly focused on linguistic improvement and conversion optimization.- [SAFE]: No data exfiltration or credential exposure; the skill only references reading a local brand context file within the agent's working directory.- [SAFE]: No remote code execution or external downloads; the skill does not use network tools or install any packages.- [SAFE]: No obfuscation found; all instructions and reference files are in plain, readable text.- [SAFE]: The skill uses a structured approach (Seven Sweeps Framework) which acts as a natural safeguard against indirect instructions by forcing the agent to evaluate the text for specific linguistic qualities.

copy-editing