The Agent Skills Directory

[SAFE]: The skill is purely instructional and informational, offering guidance on scoping, threat modeling, and reporting for AI security assessments.
[SAFE]: No executable scripts, command-line operations, or external dependencies are included in the skill files.
[SAFE]: Threat categories like prompt injection and data exfiltration are discussed conceptually as testing targets, but no active exploitation patterns or malicious instructions are present within the skill's own content.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation techniques were detected.

ai-redteam