The Agent Skills Directory

[SAFE]: No security issues were detected. The skill follows best practices for task decomposition and quality gating through its orchestrator and sub-agent architecture.- [PROMPT_INJECTION]: No attempts to override safety guidelines, bypass instructions, or extract system prompts were found in any of the 13 files analyzed.- [DATA_EXFILTRATION]: The skill accesses local marketing context files (e.g., product-context.md) for domain knowledge but does not perform any network calls or include hardcoded credentials.- [COMMAND_EXECUTION]: The skill does not use shell commands or perform system-level operations. It manages sub-tasks exclusively via the platform's Agent tool.- [EXTERNAL_DOWNLOADS]: There are no external dependencies, package installations, or remote script executions defined in the skill logic.

copywriting