The Agent Skills Directory

[SAFE]: The skill definition and accompanying scripts were thoroughly analyzed, and no malicious patterns, prompt injections, or security vulnerabilities were detected.
[COMMAND_EXECUTION]: The skill references two utility scripts (scripts/dialogue-audit.ts and scripts/voice-check.ts) configured to run under Deno with strict --allow-read boundaries. These utilities perform heuristic text analysis locally and do not interact with the operating system or run unsafe external commands.
[DATA_EXFILTRATION]: No network access or data exfiltration vectors exist in this skill. All text processing and auditing remain entirely local within the host environment.

dialogue