The Agent Skills Directory

[SAFE]: The skill follows security best practices for AI agent instructions. It focuses on a specific task (writing social media hooks) and uses localized reference files for its logic.
[SAFE]: No prompt injection or behavior override patterns were detected in the instructions or metadata.
[SAFE]: There are no external network calls, data exfiltration patterns, or attempts to access sensitive system files. References to brand-profile.md and voice.md are standard for providing context to the agent.
[SAFE]: No obfuscation, hidden characters, or encoded commands were found in any of the analyzed files.
[SAFE]: The skill does not install any external dependencies or execute remote code. It operates entirely within the agent's native text processing environment.
[SAFE]: No privilege escalation, persistence mechanisms, or dynamic execution patterns (such as runtime compilation or deserialization) are present.

hook-writer