The Agent Skills Directory

[SAFE]: The skill performs legitimate content creation tasks by reading local brand guidelines (e.g., brand/voice-profile.md) and writing marketing deliverables to the local file system. All file access patterns are restricted to the project environment and are consistent with the skill's stated purpose.\n- [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized command execution was found. The skill does not access sensitive system credentials, user environment variables, or perform any network operations.\n- [SAFE]: Mentions of external CLI integrations, such as the gws CLI, are for output formatting purposes and do not involve the runtime execution of untrusted code or the acquisition of elevated privileges.

lead-magnet