Agent Red Teaming
Use when planning or documenting an authorized security assessment of an AI agent or multi-agent workflow with safe adversarial cases, synthetic identities, canaries, and evidence-based retesting.
Install
npx skills add sandbaseai/workbuddy-skill --skill agent-red-teaminggit clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/agent-red-teaming ~/.claude/skills/agent-red-teamingPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Agent Red Teaming Find exploitable control failures without creating uncontrolled harm. Written authorization and rules of engagement are prerequisites for execution, not paperwork to complete afterward. Public reachability is not permission. ## Authorization and scope Before execution, record the named owner, authorization reference, exact targets, environment, models and configuration digest, tester identity, time window, in/out-of-scope systems and tenants, allowed techniques, rate/cost limits, stop conditions, emergency contact, cleanup owner, and evidence policy. If target-specific authorization or scope is missing, produce only a non-executable plan and threat model. Never probe a live target to infer scope. Use synthetic accounts, inert destinations, non-destructive tools, and benign canary values that grant no access. Confirm how to disable test tools, revoke credentials, restore fixtures, and report an unexpected effect before testing. ## Assessment contract Deliver: 1. Approved or explicitly pending rules of engagement. 2. A system and privilege map plus prioritized threat hypotheses. 3. A case plan with unique case IDs, target, environment, configuration digest, authorization reference, limits, stop conditions, safe oracle, and cleanup duty. 4. Execution records tied to approved cases and unique test IDs, including timestamps, observed limits, structured redacted evidence, and cleanup.
Details
- Skill name
agent-red-teaming- Repository
- sandbaseai/workbuddy-skill
- Path
skills/agent-red-teaming/SKILL.md- License
- MIT
- Repo updated
- 8 September 2026
FAQ
What does the Agent Red Teaming skill do?
Use when planning or documenting an authorized security assessment of an AI agent or multi-agent workflow with safe adversarial cases, synthetic identities, canaries, and evidence-based retesting.
How do I install the Agent Red Teaming skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill agent-red-teaming. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agent Red Teaming popular?
It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.
Related skills
Access Control Security Best Practices
9sandbaseai/workbuddy-skill
Design, review, implement, and verify least-privilege access controls across users, services, tenants, resources, and administrative workflows.
Accessibility Review
9sandbaseai/workbuddy-skill
Use when reviewing a web interface or interaction for semantic, keyboard, focus, screen-reader, ARIA, and contrast accessibility risks.
Acquire Codebase Knowledge
9sandbaseai/workbuddy-skill
Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.
Agent Session Audit
9sandbaseai/workbuddy-skill
Use when local Agent sessions need an operational audit of cost, tokens, tool failures, retry loops, latency, anomalies, health, diffs, or CI readiness.
Agent Quality Grading
9sandbaseai/workbuddy-skill
Use when evaluating how well an agent completed real tasks, used tools, communicated, or produced assets; grade each dimension from traceable evidence and keep quality separate from reliability.
Agent Skill Stack
9sandbaseai/workbuddy-skill
Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills for a multi-step workflow, asks which Skills fit a project, needs an installed-Skill audit or conflict check, has low Skill recall, wants indirect helpers such as humanizers or compliance checks, or wants a project-specific Skill Stack with controlled installation. Search local Skills, registries, GitHub, and OpenCLI; compare adoption, verified fit, safety, and overlap. Do not use for locating one known or common Skill; use the generic find-skills wo
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.