The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were found.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected.
[Obfuscation] (SAFE): No hidden or encoded content (Base64, zero-width characters, or homoglyphs) was present.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): References to pip install manim are appropriate for the skill's context and point to a well-known animation library. No suspicious remote script execution patterns or dynamic code execution methods were found.
[Privilege Escalation] (SAFE): No commands for acquiring elevated permissions (e.g., sudo, chmod 777) were detected.
[Persistence Mechanisms] (SAFE): No attempts to establish persistence across sessions (e.g., shell profile modifications or cron jobs) were identified.

manimce-best-practices