The Agent Skills Directory

COMMAND_EXECUTION (SAFE): The scripts/verify_mermaid.py script utilizes subprocess.run to invoke the mmdc utility for diagram validation. This is implemented without a shell, preventing common command injection vulnerabilities.
DATA_EXFILTRATION (SAFE): No credentials or sensitive file paths were found in the skill content. Network operations are limited to standard tool use.
PROMPT_INJECTION (SAFE): No malicious instructions aimed at overriding agent behavior or exfiltrating prompts were identified.

business-analysis