The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override system prompts were found. The skill actually includes constraints requiring user confirmation before proceeding with multiple options.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected.
[Unverifiable Dependencies & RCE] (SAFE): No external package installations or remote script execution patterns (e.g., curl|bash) are present.
[Indirect Prompt Injection] (LOW): While the skill processes user-provided architectural problems, it serves as a reasoning engine without inherent write or execute capabilities that would pose a high risk. It includes 'halt' (寸止) checkpoints to maintain human-in-the-loop control.
[Obfuscation] (SAFE): No encoded content, zero-width characters, or homoglyph-based evasion techniques were identified.

thinking