The Agent Skills Directory

[Prompt Injection] (SAFE): The skill contains purely instructional language for a reasoning framework. There are no patterns suggesting attempts to bypass safety filters or override system instructions.- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network requests were detected. The skill is designed for internal state tracking.- [Remote Code Execution] (SAFE): The skill does not include any external dependencies, package installations, or remote script execution patterns.- [Indirect Prompt Injection] (INFO): The tool ingests 'thought' strings which could potentially contain untrusted data from a user. However, the skill lacks the capabilities (network, file system write, or command execution) to act on such data maliciously. It acts as a passive container for reasoning steps.- [Obfuscation] (SAFE): No encoded strings, homoglyphs, or hidden characters were found in the file.- [Privilege Escalation] (SAFE): No commands related to administrative privileges or permission modifications are present.

sequential-thinking