New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Audit AI Agent Security

by cyberful in cyberful/cyberful

Route broad AI-agent security reviews to focused Cyberful skills across risk, model supply chain, context and capabilities, prompt injection, tool authorization, and RAG isolation.

AGPL-3.0Auto-check passedSecurity

Install Audit AI Agent Security

skills CLI
$ npx skills add cyberful/cyberful --skill audit-ai-agent-security -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cyberful/cyberful audit-ai-agent-security --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/audit-ai-agent-security .claude/skills/audit-ai-agent-security && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
audit-ai-agent-security
GitHub stars
135
Token cost
~723 tokens
SKILL.md length
234 words
Files
5 (incl. references)
Skills in repo
85
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Route broad AI-agent security reviews to focused Cyberful skills across risk, model supply chain, context and capabilities, prompt injection, tool authorization, and RAG isolation.

  • An authorized LLM
  • SKILL.md covers Route by security question and Coordinate without duplicating…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Agent assessment spans several AI security boundaries

What it does

Audit AI Agent Security is an agent skill from cyberful/cyberful. Route broad AI-agent security reviews to focused Cyberful skills across risk, model supply chain, context and capabilities, prompt injection, tool authorization, and RAG isolation. Use when an authorized LLM or agent assessment spans several AI security boundaries or the correct specialist is not yet clear.

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/agent-tool-boundaries.md` and `references/llm-risk-catalog.md`).

It sits in Security, covering Prompt injection and agent security. The repository describes itself as: Cyberful is an open-source AI Red Team for discovering, exploiting, verifying, and remediating vulnerabilities. The licence is AGPL-3.0.

When your agent uses it

  • An authorized LLM
  • Agent assessment spans several AI security boundaries
  • The correct specialist is not yet clear

Example prompts

  • “/audit-ai-agent-security”

What it can do on your machine

Read from SKILL.md and the folder at commit ec598a6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audit AI Agent Security loads about 723 tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~723
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 234 words, ~723 tokens.

Download SKILL.mdSave it as .claude/skills/audit-ai-agent-security/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
audit-ai-agent-security
description
Route broad AI-agent security reviews to focused Cyberful skills across risk, model supply chain, context and capabilities, prompt injection, tool authorization, and RAG isolation. Use when an authorized LLM or agent assessment spans several AI security boundaries or the correct specialist is not yet clear.
metadata.domain
ai-security
metadata.subdomain
agent-security-routing
metadata.triggers
AI agent security audit, LLM application security review, agentic AI assessment, MCP security review, RAG and tool security
metadata.tags
LLM, agents, MCP, RAG, capability-security

Audit AI and Agent Security

Use this skill only to establish scope and route the work. Do not reproduce a specialist's procedure here.

Route by security question

  • Use plan-authorized-ai-red-team to define identities, scope, stop conditions, canaries, and coverage before active testing.
  • Use assess-ai-system-risk for an architecture-wide AI risk assessment and control posture.
  • Use audit-ai-model-supply-chain for model, adapter, dataset, artifact, registry, and loading provenance.
  • Use trace-ai-context-capabilities to reconstruct instruction, memory, retrieval, identity, delegation, and tool reachability.
  • Use test-ai-prompt-injection when untrusted content may influence model behavior across direct, indirect, stored, multimodal, or tool-result channels.
  • Use test-ai-tool-authorization when tool selection, canonical arguments, credentials, approvals, destinations, or delegated authority are the security boundary.
  • Use test-rag-isolation-integrity for cross-tenant retrieval, ACL drift, poisoning, cache isolation, or persistent memory integrity.

Read agent-tool-boundaries.md only while deciding whether capability tracing or tool-authorization testing owns a chain. Read llm-risk-catalog.md only for broad coverage reconciliation. Read rag-memory-supply-chain.md only while splitting retrieval, memory, and supply-chain work.

Coordinate without duplicating work

Create a shared capability and evidence ledger, assign each hypothesis to one specialist, and preserve cross-skill dependencies. A refusal, surprising text response, or prompt disclosure is not itself a vulnerability; require a failed deterministic boundary and a security-relevant effect. Keep credentials, tenant checks, destination policy, approvals, budgets, and output encoding outside model instructions.

Deliver the routing decision, uncovered surfaces, dependencies between specialists, and consolidated evidence references. Return here only when new architecture evidence changes the routing.

© cyberful, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in cyberful/builtin/skills/audit-ai-agent-security of cyberful/cyberful.

  • SKILL.md
  • agents/openai.yaml
  • references/agent-tool-boundaries.md
  • references/llm-risk-catalog.md
  • references/rag-memory-supply-chain.md

Open the folder on GitHubat commit ec598a6

Compare with similar skills

Audit AI Agent Security next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audit AI Agent Security compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit AI Agent Security this skillcyberful/cyberful135—~723Automated safety check: PassAGPL-3.0
Skill Scannergetsentry/skills1k4 repos~2.5kAutomated safety check: WarnApache-2.0
Forensifyalexgreensh/repo-forensics190—~2.5kAutomated safety check: NotesCustom licence
Hol Guardhashgraph-online/hol-guard838—~542Automated safety check: PassApache-2.0
Kesekit Checkcdppcorp/KESE-KIT360—~1.3kAutomated safety check: PassMIT
Setuphashgraph-online/hol-guard838—~443Automated safety check: PassApache-2.0

Similar skills

  • Skill Scanner

    getsentry/skills

    Official

    Scan agent skills for security issues. An agent skill from getsentry/skills.

    1k GitHub starsUsed in 4 repos~2.5k tokens
    SecurityAuto-check: warnings

  • Forensify

    alexgreensh/repo-forensics

    Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.

    190 GitHub stars~2.5k tokensUpdated 13 days ago
    SecurityAuto-check: notes

  • Hol Guard

    hashgraph-online/hol-guard

    Run HOL Guard scanner and guard operations via uv run hol-guard.

    838 GitHub stars~542 tokensUpdated today
    SecurityAuto-check passed

  • Kesekit Check

    cdppcorp/KESE-KIT

    Run a pre-deployment security compliance checklist based on KISA guidelines.

    360 GitHub stars~1.3k tokensUpdated 6 mo ago
    SecurityAuto-check passed

  • Setup

    hashgraph-online/hol-guard

    Install or initialize HOL Guard local runtime protection for Claude Code.

    838 GitHub stars~443 tokensUpdated today
    SecurityAuto-check passed

  • Clawscan CLI

    openclaw/clawscan

    A skill your agent uses when running or explaining the ClawScan CLI, including one-off agent-skill scans, benchmark runs, scanner fixtures, judge harness commands, env var validation, and…

    143 GitHub stars~3k tokensUpdated 3 days ago
    SecurityAuto-check passed

More from cyberful/cyberful

All 85 skills in this repo

  • Audit Infrastructure As Code

    cyberful/cyberful

    Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.

    135 GitHub stars~649 tokensUpdated 1 mo ago
    Auto-check passed

  • Audit Kubernetes Policy Enforcement

    cyberful/cyberful

    Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment evidence.

    135 GitHub stars~610 tokensUpdated 1 mo ago
    Auto-check passed

  • Audit Pci Dss Penetration Test Evidence

    cyberful/cyberful

    Audit PCI DSS penetration-test methodology, scope, internal and external reports, segmentation results, tester independence, remediation, retesting, retention, and multi-tenant support evidence.

    135 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Content Discovery

    cyberful/cyberful

    Design and interpret advanced content discovery with ffuf and complementary web fuzzers.

    135 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Network Recon

    cyberful/cyberful

    Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.

    135 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Sast Toolchain

    cyberful/cyberful

    Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.

    135 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Audit AI Agent Security

What does Audit AI Agent Security do?

Route broad AI-agent security reviews to focused Cyberful skills across risk, model supply chain, context and capabilities, prompt injection, tool authorization, and RAG isolation. Audit AI Agent Security is an agent skill from cyberful/cyberful. Route broad AI-agent security reviews to focused Cyberful skills across risk, model supply chain, context and capabilities, prompt injection, tool authorization, and RAG isolation.

When should I use Audit AI Agent Security?

Audit AI Agent Security fits situations like: an authorized LLM; agent assessment spans several AI security boundaries; the correct specialist is not yet clear.

How do I install Audit AI Agent Security in Claude Code?

Run `npx skills add cyberful/cyberful --skill audit-ai-agent-security -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/audit-ai-agent-security in cyberful/cyberful) into .claude/skills/audit-ai-agent-security in your project. Claude Code loads it when a task matches its description.

How do I install Audit AI Agent Security in Codex?

Run `npx skills add cyberful/cyberful --skill audit-ai-agent-security -a codex`. Or copy the skill folder (cyberful/builtin/skills/audit-ai-agent-security in cyberful/cyberful) into .agents/skills/audit-ai-agent-security in your project. Codex loads it when a task matches its description.

Can I use Audit AI Agent Security in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyberful/cyberful --skill audit-ai-agent-security -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-ai-agent-security, .gemini/skills/audit-ai-agent-security, .github/skills/audit-ai-agent-security and .opencode/skills/audit-ai-agent-security in your project.

What does Audit AI Agent Security need to run?

SKILL.md names no scripts, command-line tools or credentials: Audit AI Agent Security is instructions for the agent only.

Does Audit AI Agent Security access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Audit AI Agent Security safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audit AI Agent Security use?

Audit AI Agent Security is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit AI Agent Security use?

About 723 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Audit AI Agent Security?

Skills that share tags, products or a category with Audit AI Agent Security: Skill Scanner (getsentry/skills, 1k stars), Forensify (alexgreensh/repo-forensics, 190 stars), Hol Guard (hashgraph-online/hol-guard, 838 stars) and Kesekit Check (cdppcorp/KESE-KIT, 360 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit AI Agent Security?

cyberful (a GitHub organization) maintains it in cyberful/cyberful, which has 135 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 24, 2026.

Source: cyberful/cyberful on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.