The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or high-risk behaviors were identified in the analyzed files. The skill functions as a character persona and intellectual framework for the AI agent.
[PROMPT_INJECTION]: The instructions in SKILL.md define a specific analytical perspective based on Foucauldian philosophy. There are no attempts to bypass safety filters, ignore system instructions, or use jailbreak techniques.
[DATA_EXFILTRATION]: No network calls, file reading operations, or hardcoded credentials were found. The skill does not access sensitive user data or external environments.
[REMOTE_CODE_EXECUTION]: The skill does not contain any executable scripts, remote downloads, or package installation commands beyond the standard informational installation reference in the documentation.
[COMMAND_EXECUTION]: There are no shell commands, dynamic context injections, or subprocess calls present in the skill's instructions or examples.
[NO_CODE]: The skill is implemented as a set of Markdown files and YAML metadata, defining a role-play protocol and knowledge base without implementing any logical code or tools.

foucault-perspective