Test deterministic authorization around AI tool discovery, selection, canonical arguments, credentials, tenants, destinations, approvals, delegation, retries, and effects.
$ npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cyberful/cyberful test-ai-tool-authorization --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/test-ai-tool-authorization .claude/skills/test-ai-tool-authorization && rm -rf skills-srcUse ~/.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/
Install the "test-ai-tool-authorization" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-tool-authorization into .claude/skills/test-ai-tool-authorization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-tool-authorization", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-tool-authorizationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cyberful/cyberful test-ai-tool-authorization --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cyberful/builtin/skills/test-ai-tool-authorization .agents/skills/test-ai-tool-authorization && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "test-ai-tool-authorization" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-tool-authorization into .agents/skills/test-ai-tool-authorization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-tool-authorization", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cyberful/cyberful test-ai-tool-authorization --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cyberful/builtin/skills/test-ai-tool-authorization .cursor/skills/test-ai-tool-authorization && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "test-ai-tool-authorization" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-tool-authorization into .cursor/skills/test-ai-tool-authorization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-tool-authorization", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cyberful/cyberful.git --path cyberful/builtin/skills/test-ai-tool-authorization--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cyberful/cyberful test-ai-tool-authorization --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cyberful/builtin/skills/test-ai-tool-authorization .gemini/skills/test-ai-tool-authorization && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "test-ai-tool-authorization" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-tool-authorization into .gemini/skills/test-ai-tool-authorization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-tool-authorization", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cyberful/cyberful test-ai-tool-authorizationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .github/skills && cp -r skills-src/cyberful/builtin/skills/test-ai-tool-authorization .github/skills/test-ai-tool-authorization && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "test-ai-tool-authorization" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-tool-authorization into .github/skills/test-ai-tool-authorization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-tool-authorization", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cyberful/cyberful test-ai-tool-authorization --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cyberful/builtin/skills/test-ai-tool-authorization .opencode/skills/test-ai-tool-authorization && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "test-ai-tool-authorization" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-tool-authorization into .opencode/skills/test-ai-tool-authorization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-tool-authorization", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
test-ai-tool-authorizationTest deterministic authorization around AI tool discovery, selection, canonical arguments, credentials, tenants, destinations, approvals, delegation, retries, and effects.
Test AI Tool Authorization is an agent skill from cyberful/cyberful. Test deterministic authorization around AI tool discovery, selection, canonical arguments, credentials, tenants, destinations, approvals, delegation, retries, and effects. Use when model refusal is insufficient and the host or gateway must enforce an authorized capability boundary.
Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/tool-authorization-evidence.schema.json` and `assets/tool-authorization-probe.example.json`).
It sits in Backend & APIs, covering Authorization and RBAC. 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.
Read from SKILL.md and the folder at commit ec598a6. It shows what the files ask for, not the result of running them.
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.
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Test AI Tool Authorization loads about 549 tokens when it runs, and up to ~774 if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 149 words of instructions outside code blocks.
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.
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); the scripts in this folder are not scanned.
The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 149 words, ~549 tokens.
.claude/skills/test-ai-tool-authorization/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.Treat authorization as a host decision over a canonical action. Model refusal, hidden instructions, and tool descriptions are not enforcement.
Record actor, tenant, session, model route, tool identity/schema, requested arguments, resolved resource, destination, credential, approval, effect, retry/delegation context, and expected decision. Read references/tool-authorization-matrix.md for negative cases.
Stage scripts/run_tool_authorization_probe.py, its manifest, and the probe example for matched allowed/denied HTTP actions. Its JSON carries defense-in-depth campaign constraints, never authority. Actual authorization and non-loopback routing stay in Cyberful's mission-bound gateway or ZAP route, using only runtime standard proxy and CA environment. Reflected credentials are redacted before cumulative-bounded evidence is retained.
Compare canonical action and external effect, not response prose. Test resource, tenant, destination, recipient, amount, scope, credential, approval freshness, retry, fallback, and delegation boundaries using tester-owned fixtures. Report the smallest unauthorized effect, the missing enforcement owner, control comparison, and cleanup.
© 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
SKILL.md and 8 other files (scripts, references, assets) in cyberful/builtin/skills/test-ai-tool-authorization of cyberful/cyberful.
Open the folder on GitHubat commit ec598a6
Test AI Tool Authorization 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Test AI Tool Authorization this skillcyberful/cyberful | 135 | — | ~549 | Automated safety check: Pass | AGPL-3.0 | |
| Implementing Device Posture Assessment In Zero Trustmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | |
| Audit Reconccashwell/evm-cortex | 131 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Executing Nist Rmf Authorization To Operatemukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Sec Checkwaynesutton/markdown-site | 628 | — | ~753 | Automated safety check: Pass | MIT | |
| Security Threat Modelmajiayu000/spellbook | 287 | — | ~561 | Automated safety check: Pass | MIT |
mukul975/Anthropic-Cybersecurity-Skills
Implements device posture assessment as a zero trust access control by integrating endpoint health signals from CrowdStrike ZTA, Microsoft Intune, and Jamf into conditional access policies that…
ccashwell/evm-cortex
A skill your agent uses when performing initial audit reconnaissance.
mukul975/Anthropic-Cybersecurity-Skills
Drive a federal system through the NIST Risk Management Framework (SP 800-37 Rev 2) to an Authorization to Operate (ATO): Prepare, Categorize (FIPS 199), Select a control baseline (FIPS 200 / SP…
waynesutton/markdown-site
Security review checklist for Convex functions, auth logic, public queries, admin routes, webhooks, uploads, and AI-generated code.
majiayu000/spellbook
Threat-model product features, APIs, data flows, secrets, permissions, supply-chain changes, auth boundaries, and risky code paths before or during implementation.
coralogix/cx-cli
A skill your agent uses when the user asks "who has access", "audit permissions", "check user roles", "list API keys", "review access controls", "rotate API keys", "create API key", "delete expired…
cyberful/cyberful
Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.
cyberful/cyberful
Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment 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.
cyberful/cyberful
Design and interpret advanced content discovery with ffuf and complementary web fuzzers.
cyberful/cyberful
Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.
cyberful/cyberful
Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.
Categories
Test deterministic authorization around AI tool discovery, selection, canonical arguments, credentials, tenants, destinations, approvals, delegation, retries, and effects. Test AI Tool Authorization is an agent skill from cyberful/cyberful. Test deterministic authorization around AI tool discovery, selection, canonical arguments, credentials, tenants, destinations, approvals, delegation, retries, and effects.
Test AI Tool Authorization fits situations like: model refusal is insufficient and the host; gateway must enforce an authorized capability boundary.
Run `npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/test-ai-tool-authorization in cyberful/cyberful) into .claude/skills/test-ai-tool-authorization in your project. Claude Code loads it when a task matches its description.
Run `npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a codex`. Or copy the skill folder (cyberful/builtin/skills/test-ai-tool-authorization in cyberful/cyberful) into .agents/skills/test-ai-tool-authorization in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyberful/cyberful --skill test-ai-tool-authorization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-ai-tool-authorization, .gemini/skills/test-ai-tool-authorization, .github/skills/test-ai-tool-authorization and .opencode/skills/test-ai-tool-authorization in your project.
Going by SKILL.md and its folder, Test AI Tool Authorization needs Python for the scripts in its folder. Our summary lists: Python 3.
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.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Test AI Tool Authorization 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.
About 549 tokens (SKILL.md is roughly 2.2k 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 225 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Test AI Tool Authorization: Implementing Device Posture Assessment In Zero Trust (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Audit Recon (ccashwell/evm-cortex, 131 stars), Executing Nist Rmf Authorization To Operate (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Sec Check (waynesutton/markdown-site, 628 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.
