The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and guidance for detection authoring. It provides a taxonomy of Okta System Log events, authentication flows, and known attack patterns (such as Scattered Spider or session hijacking) to help security analysts write better detection logic.
[NO_CODE]: No executable scripts (.py, .js, .sh), configuration files, or binary assets are included in the skill. It purely teaches the agent how to interpret specific telemetry fields.
[PROMPT_INJECTION]: No instructions were found that attempt to override the agent's system prompt, bypass safety filters, or use role-play to evade constraints.
[DATA_EXFILTRATION]: No network operations (curl, wget, fetch) or access to sensitive local file paths (e.g., .ssh, .aws) were detected.
[REMOTE_CODE_EXECUTION]: No external dependencies (npm, pip) or remote code download and execution patterns are present.
[OBFUSCATION]: The content is clear and readable. No hidden characters, Base64 encoding, or homoglyph attacks were detected in the documentation.

okta-identity