The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to bypass safety filters or override agent behavior.- [Data Exposure & Exfiltration] (SAFE): No access to sensitive files or unauthorized network communication detected.- [Obfuscation] (SAFE): No encoded or hidden content detected.- [Unverifiable Dependencies] (SAFE): Only standard scientific libraries are referenced.- [Privilege Escalation] (SAFE): No commands requesting elevated permissions were found.- [Persistence Mechanisms] (SAFE): No attempts to establish persistent access or modify system startup scripts.- [Metadata Poisoning] (SAFE): Metadata accurately reflects the skill's functionality.- [Indirect Prompt Injection] (LOW): The skill handles data for visualization and supports LaTeX rendering via the PGF backend. While LaTeX environments can be configured unsafely (e.g., shell-escape), the instructions provided follow standard professional practices for scientific publishing.- [Time-Delayed / Conditional Attacks] (SAFE): No conditional logic based on time or external state detected.- [Dynamic Execution] (SAFE): No use of eval, exec, or unsafe deserialization of untrusted data.

matplotlib-pro