The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No instructions found that attempt to override agent behavior, bypass safety filters, or extract system prompts. The triggers are correctly scoped to Manim-related tasks.
[DATA_EXFILTRATION] (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected. All Python examples and markdown files focus strictly on animation logic.
[OBFUSCATION] (SAFE): No Base64, zero-width characters, or hidden Unicode tags were found. The code and documentation are transparent and human-readable.
[REMOTE_CODE_EXECUTION] (SAFE): No patterns of downloading and piping remote scripts to shells (e.g., curl|bash) were found. Python scripts use standard libraries (manim, numpy, scipy) appropriate for the task.
[DYNAMIC_EXECUTION] (SAFE): No unsafe use of eval(), exec(), or dynamic loading of modules from untrusted paths was detected.
[PRIVILEGE_ESCALATION] (SAFE): No use of sudo, administrative commands, or attempts to modify system-level configurations were identified.
[PERSISTENCE] (SAFE): No attempts to create cron jobs, startup scripts, or background services were found.
[INDIRECT_PROMPT_INJECTION] (SAFE): While the skill processes user mathematical code for visualization, it does not ingest external data from untrusted sources like third-party APIs or web pages that could inject malicious instructions.

manimce-best-practices