The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found.
[Data Exposure & Exfiltration] (SAFE): No commands accessing sensitive files, environment variables, or performing unauthorized network requests were detected.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): Although the skill specifies Bash(python:*) and Bash(pip:*) in its allowed tools, there are no scripts or configuration files that initiate external downloads or execute remote code.
[Obfuscation] (SAFE): No Base64, zero-width characters, or other encoding techniques intended to hide malicious content were identified.
[Persistence Mechanisms] (SAFE): No attempts to modify shell profiles, cron jobs, or system services were found.

roc-curve-plotter