skills sourced live from GitHub · all skills listed are free · each skill is provided under its author's license.
home / Security / AI Red Teaming Skill by @BagelHole
The skill is the security/ai/ai-red-teaming folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.
Structured red-team exercises for LLM apps covering jailbreaks, data exfiltration, harmful output and agent tool abuse, with scoring and reporting.
Provides a program design, test categories, adversarial prompt library, runner configuration, risk scoring and report template.
Written and maintained by @BagelHole. It is published under the MIT license, which allows reuse with attribution. See the author profile. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.
(Excerpt. Full file: https://github.com/BagelHole/DevOps-Security-Agent-Skills/blob/main/security/ai/ai-red-teaming/SKILL.md)
Excerpt only, quoted from the author's repository. Open the repository for the complete file.