Skill Scanner
getsentry/skills
Scan agent skills for security issues. An agent skill from getsentry/skills.
Test whether authorized direct or indirect untrusted content can alter an AI system's protected behavior, context use, memory, retrieval, output handling, or downstream capability.
Install Test AI Prompt Injection
$ npx skills add cyberful/cyberful --skill test-ai-prompt-injection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cyberful/cyberful test-ai-prompt-injection --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-prompt-injection .claude/skills/test-ai-prompt-injection && 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-prompt-injection" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-prompt-injection into .claude/skills/test-ai-prompt-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-prompt-injection", 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-prompt-injectionType 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-prompt-injection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cyberful/cyberful test-ai-prompt-injection --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-prompt-injection .agents/skills/test-ai-prompt-injection && 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-prompt-injection" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-prompt-injection into .agents/skills/test-ai-prompt-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-prompt-injection", 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-prompt-injection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cyberful/cyberful test-ai-prompt-injection --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-prompt-injection .cursor/skills/test-ai-prompt-injection && 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-prompt-injection" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-prompt-injection into .cursor/skills/test-ai-prompt-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-prompt-injection", 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-prompt-injection--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-prompt-injection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cyberful/cyberful test-ai-prompt-injection --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-prompt-injection .gemini/skills/test-ai-prompt-injection && 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-prompt-injection" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-prompt-injection into .gemini/skills/test-ai-prompt-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-prompt-injection", 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-prompt-injectionInstalls 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-prompt-injection -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-prompt-injection .github/skills/test-ai-prompt-injection && 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-prompt-injection" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-prompt-injection into .github/skills/test-ai-prompt-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-prompt-injection", 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-prompt-injection -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-prompt-injection --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-prompt-injection .opencode/skills/test-ai-prompt-injection && 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-prompt-injection" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-ai-prompt-injection into .opencode/skills/test-ai-prompt-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-ai-prompt-injection", 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.
Facts
- Skill name
test-ai-prompt-injection- GitHub stars
- 135
- Token cost
- ~538 tokens
- SKILL.md length
- 143 words
- Files
- 9 (incl. scripts, references, assets)
- Skills in repo
- 85
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Test whether authorized direct or indirect untrusted content can alter an AI system's protected behavior, context use, memory, retrieval, output handling, or downstream capability.
- Bounded prompt-injection experiments with benign markers and deterministic control comparisons
- SKILL.md covers Define the discriminator and Confirm and report
- Runs Python scripts from its folder
- Tasks that involve Prompt injection and agent security
What it does
Test AI Prompt Injection is an agent skill from cyberful/cyberful. Test whether authorized direct or indirect untrusted content can alter an AI system's protected behavior, context use, memory, retrieval, output handling, or downstream capability. Use for bounded prompt-injection experiments with benign markers and deterministic control comparisons.
Its SKILL.md is about 540 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/prompt-injection-evidence.schema.json` and `assets/prompt-injection-probe.example.json`).
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
- Bounded prompt-injection experiments with benign markers and deterministic control comparisons
- Tasks that involve Prompt injection and agent security
Example prompts
- “/test-ai-prompt-injection”
Requirements
- Python 3
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
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.
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
Test AI Prompt Injection loads about 538 tokens when it runs, and up to ~772 if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 143 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.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 143 words, ~538 tokens.
Download SKILL.mdSave it as
.claude/skills/test-ai-prompt-injection/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- test-ai-prompt-injection
- description
- Test whether authorized direct or indirect untrusted content can alter an AI system's protected behavior, context use, memory, retrieval, output handling, or downstream capability. Use for bounded prompt-injection experiments with benign markers and deterministic control comparisons.
- metadata.domain
- ai-security
- metadata.subdomain
- prompt-injection
- metadata.triggers
- test AI prompt injection, indirect prompt injection, stored prompt injection, tool output injection, multimodal instruction injection
- metadata.tags
- prompt-injection, LLM, indirect-injection, canary, untrusted-content, control-comparison
Test AI Prompt Injection
Demonstrate a failed boundary and consequential effect, not merely surprising text.
Define the discriminator
For each source, specify protected instruction, untrusted channel, benign unique marker, expected safe behavior, control input, target capability, maximum effect, and cleanup. Read references/prompt-injection-evidence.md before escalating beyond instruction influence.
Stage scripts/run_prompt_injection_probe.py, its manifest, and the probe example for bounded HTTP comparisons. The JSON records defense-in-depth campaign constraints, never authority. Cyberful's mission-bound gateway or ZAP route supplies the actual authorization boundary, standard proxy and CA environment, and the only path to non-loopback targets. Responses are cumulative-bounded and environment secrets are redacted before evidence is retained.
Confirm and report
Compare control and candidate across model route, retrieved context, tool request, canonical arguments, memory mutation, output consumer, and external effect. Stop at the smallest permitted proof. Record source, transformations, preconditions, model/tool path, failed deterministic control, reproducibility, 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
Files
SKILL.md and 8 other files (scripts, references, assets) in cyberful/builtin/skills/test-ai-prompt-injection of cyberful/cyberful.
- SKILL.md
- agents/openai.yaml
- assets/prompt-injection-evidence.schema.json
- assets/prompt-injection-probe.example.json
- assets/prompt-injection-probe.schema.json
- references/prompt-injection-evidence.md
- scripts/manifest.json
- scripts/run_prompt_injection_probe.py
- tests/test_run_prompt_injection_probe.py
Open the folder on GitHubat commit ec598a6
Compare with similar skills
Test AI Prompt Injection 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 Prompt Injection this skillcyberful/cyberful | 135 | — | ~538 | Automated safety check: Pass | AGPL-3.0 | |
| Skill Scannergetsentry/skills | 1k | 4 repos | ~2.5k | Automated safety check: Warn | Apache-2.0 | |
| Forensifyalexgreensh/repo-forensics | 190 | — | ~2.5k | Automated safety check: Notes | Custom licence | |
| Hol Guardhashgraph-online/hol-guard | 845 | — | ~542 | Automated safety check: Pass | Apache-2.0 | |
| Kesekit Checkcdppcorp/KESE-KIT | 360 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Setuphashgraph-online/hol-guard | 845 | — | ~443 | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Forensify
alexgreensh/repo-forensics
Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.
Hol Guard
hashgraph-online/hol-guard
Run HOL Guard scanner and guard operations via uv run hol-guard.
Kesekit Check
cdppcorp/KESE-KIT
Run a pre-deployment security compliance checklist based on KISA guidelines.
Setup
hashgraph-online/hol-guard
Install or initialize HOL Guard local runtime protection for Claude Code.
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…
More from cyberful/cyberful
All 85 skills in this repoAudit Infrastructure As Code
cyberful/cyberful
Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.
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.
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.
Operate Content Discovery
cyberful/cyberful
Design and interpret advanced content discovery with ffuf and complementary web fuzzers.
Operate Network Recon
cyberful/cyberful
Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.
Operate Sast Toolchain
cyberful/cyberful
Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.
Related
Categories
Questions about Test AI Prompt Injection
What does Test AI Prompt Injection do?
Test whether authorized direct or indirect untrusted content can alter an AI system's protected behavior, context use, memory, retrieval, output handling, or downstream capability. Test AI Prompt Injection is an agent skill from cyberful/cyberful. Test whether authorized direct or indirect untrusted content can alter an AI system's protected behavior, context use, memory, retrieval, output handling, or downstream capability.
When should I use Test AI Prompt Injection?
Test AI Prompt Injection fits situations like: bounded prompt-injection experiments with benign markers and deterministic control comparisons; tasks that involve Prompt injection and agent security.
How do I install Test AI Prompt Injection in Claude Code?
Run `npx skills add cyberful/cyberful --skill test-ai-prompt-injection -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/test-ai-prompt-injection in cyberful/cyberful) into .claude/skills/test-ai-prompt-injection in your project. Claude Code loads it when a task matches its description.
How do I install Test AI Prompt Injection in Codex?
Run `npx skills add cyberful/cyberful --skill test-ai-prompt-injection -a codex`. Or copy the skill folder (cyberful/builtin/skills/test-ai-prompt-injection in cyberful/cyberful) into .agents/skills/test-ai-prompt-injection in your project. Codex loads it when a task matches its description.
Can I use Test AI Prompt Injection 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 test-ai-prompt-injection -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-prompt-injection, .gemini/skills/test-ai-prompt-injection, .github/skills/test-ai-prompt-injection and .opencode/skills/test-ai-prompt-injection in your project.
What does Test AI Prompt Injection need to run?
Going by SKILL.md and its folder, Test AI Prompt Injection needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Test AI Prompt Injection 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 Test AI Prompt Injection 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Test AI Prompt Injection use?
Test AI Prompt Injection 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 Test AI Prompt Injection use?
About 538 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 234 tokens, read only when the agent opens those files.
What are the alternatives to Test AI Prompt Injection?
Skills that share tags, products or a category with Test AI Prompt Injection: Skill Scanner (getsentry/skills, 1k stars), Forensify (alexgreensh/repo-forensics, 190 stars), Hol Guard (hashgraph-online/hol-guard, 845 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 Test AI Prompt Injection?
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.