The Agent Skills Directory

Data Exposure & Exfiltration (SAFE): No access to sensitive system paths or unauthorized network communication detected. Code snippets in the documentation use standard placeholder domains for demonstration purposes.
Unverifiable Dependencies & Remote Code Execution (SAFE): The validation script scripts/validate.py uses standard Python libraries and does not perform any external package installations or remote script executions.
Dynamic Execution (SAFE): The Python scripts utilize yaml.safe_load() instead of the unsafe load() method, preventing potential arbitrary code execution via malicious YAML payloads.
Indirect Prompt Injection (SAFE): The skill defines strict validation for its input parameters (e.g., the topic parameter uses a specific regex whitelist), minimizing the risk of prompt-based attacks through user input.

kotlin-ktor