The Agent Skills Directory

[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file paths were detected. The scripts do not perform network operations.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The Python scripts rely on standard libraries and the PyYAML package. No remote code execution patterns, such as piping curl to a shell, were found.
[Prompt Injection] (SAFE): The documentation files (output-patterns.md, workflows.md) provide benign structural templates and examples. There are no instructions aimed at bypassing AI safety guardrails or overriding system prompts.
[Dynamic Execution] (SAFE): The scripts use yaml.safe_load() for parsing configuration, which is the recommended secure method to prevent arbitrary code execution during YAML deserialization. No use of eval() or exec() on untrusted input was identified.

skill-creator