The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding products, audiences, and business goals. It incorporates a mandatory validation step ('Copy Brief Lock') which requires explicit user confirmation of the gathered context before the agent proceeds to generate copy, effectively serving as a human-in-the-loop boundary marker. There are no associated tool capabilities (file system access, network operations, or code execution) that could be exploited via malicious input.
[REMOTE_CODE_EXECUTION]: No external scripts, package installations, or remote execution patterns were detected. The skill operates entirely through natural language instructions.
[DATA_EXFILTRATION]: No network operations, sensitive file paths, or hardcoded credentials were found. The skill does not attempt to send data to external servers.
[OBFUSCATION]: The content is presented in clear, readable markdown. No Base64, zero-width characters, homoglyphs, or other encoding techniques were used to hide instructions.

copywriting