The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions were found that attempt to override agent behavior, bypass safety filters, or extract system prompts. The content is purely instructional for routing logic.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network communication patterns (like curl or fetch) were detected.
[Remote Code Execution] (SAFE): The skill does not include any executable code, package dependencies, or remote script download patterns.
[Obfuscation] (SAFE): No hidden characters, Base64 encoding, or homoglyph-based evasion techniques were identified.
[Indirect Prompt Injection] (SAFE): While the skill defines how to handle untrusted user input by routing it to other tools, this routing file itself possesses no capabilities (such as file-writing or network access) that could be exploited.

reasoning-router