Skill Scanner
getsentry/skills
Scan agent skills for security issues. An agent skill from getsentry/skills.
Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy.
Install Prompt Injection Test
$ npx skills add OWASP/secure-agent-playbook --skill prompt-injection-test -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OWASP/secure-agent-playbook prompt-injection-test --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/OWASP/secure-agent-playbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ai-security-skills/skills/prompt-injection-test .claude/skills/prompt-injection-test && 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 "prompt-injection-test" agent skill from https://github.com/OWASP/secure-agent-playbook/tree/main/plugins/ai-security-skills/skills/prompt-injection-test into .claude/skills/prompt-injection-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-injection-test", 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/OWASP/secure-agent-playbook/tree/main/plugins/ai-security-skills/skills/prompt-injection-testType 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 OWASP/secure-agent-playbook --skill prompt-injection-test -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OWASP/secure-agent-playbook prompt-injection-test --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OWASP/secure-agent-playbook.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/ai-security-skills/skills/prompt-injection-test .agents/skills/prompt-injection-test && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prompt-injection-test" agent skill from https://github.com/OWASP/secure-agent-playbook/tree/main/plugins/ai-security-skills/skills/prompt-injection-test into .agents/skills/prompt-injection-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-injection-test", 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 OWASP/secure-agent-playbook --skill prompt-injection-test -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OWASP/secure-agent-playbook prompt-injection-test --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OWASP/secure-agent-playbook.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/ai-security-skills/skills/prompt-injection-test .cursor/skills/prompt-injection-test && 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 "prompt-injection-test" agent skill from https://github.com/OWASP/secure-agent-playbook/tree/main/plugins/ai-security-skills/skills/prompt-injection-test into .cursor/skills/prompt-injection-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-injection-test", 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/OWASP/secure-agent-playbook.git --path plugins/ai-security-skills/skills/prompt-injection-test--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 OWASP/secure-agent-playbook --skill prompt-injection-test -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OWASP/secure-agent-playbook prompt-injection-test --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OWASP/secure-agent-playbook.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/ai-security-skills/skills/prompt-injection-test .gemini/skills/prompt-injection-test && 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 "prompt-injection-test" agent skill from https://github.com/OWASP/secure-agent-playbook/tree/main/plugins/ai-security-skills/skills/prompt-injection-test into .gemini/skills/prompt-injection-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-injection-test", 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 OWASP/secure-agent-playbook prompt-injection-testInstalls 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 OWASP/secure-agent-playbook --skill prompt-injection-test -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OWASP/secure-agent-playbook.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/ai-security-skills/skills/prompt-injection-test .github/skills/prompt-injection-test && 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 "prompt-injection-test" agent skill from https://github.com/OWASP/secure-agent-playbook/tree/main/plugins/ai-security-skills/skills/prompt-injection-test into .github/skills/prompt-injection-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-injection-test", 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 OWASP/secure-agent-playbook --skill prompt-injection-test -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OWASP/secure-agent-playbook prompt-injection-test --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OWASP/secure-agent-playbook.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/ai-security-skills/skills/prompt-injection-test .opencode/skills/prompt-injection-test && 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 "prompt-injection-test" agent skill from https://github.com/OWASP/secure-agent-playbook/tree/main/plugins/ai-security-skills/skills/prompt-injection-test into .opencode/skills/prompt-injection-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-injection-test", 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
prompt-injection-test- GitHub stars
- 187
- Token cost
- ~758 tokens
- SKILL.md length
- 315 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- CC-BY-4.0
At a glance
Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy.
- Works in 7 steps: Scope and Input Surface Mapping —… → Test by Attack Intent (13 intents) — For… → Test by Attack Technique (18 techniques)… → …
- Red-teaming AI apps
- SKILL.md covers Steps, Output and OWASP References
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Prompt Injection Test is an agent skill from OWASP/secure-agent-playbook. Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy. Use when red-teaming AI apps, validating guardrails, or deepening LLM01 (Prompt Injection) assessments.
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Security, covering Prompt injection and agent security. The repository describes itself as: OWASP Secure Agent Playbook Project. The licence is CC-BY-4.0.
When your agent uses it
- Red-teaming AI apps
- Validating guardrails
- Deepening LLM01 (Prompt Injection) assessments
Example prompts
- “/prompt-injection-test”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Scope and Input Surface Mapping — Identify all paths where attacker-controlled content reaches the LLM: direct (chat, API params) and…
- Test by Attack Intent (13 intents) — For each authorized intent, attempt to achieve the attacker's goal
- Test by Attack Technique (18 techniques) — Apply known payload construction methods
- Apply Evasion Layers (20 evasions) — When techniques are blocked, retry with obfuscation
- Execute Test Matrix — Combine intents x techniques x evasions. Prioritize: high-impact intents first, indirect surfaces second, evasion…
- Assess Results — For each successful injection, document: severity, attack path (intent + technique + evasion + surface), exact payload…
- Defense Validation — Check the 5-layer defense checklist: ecosystem hardening, model guardrails, prompt-layer defenses, data-layer…
What it can do on your machine
Read from SKILL.md and the folder at commit 1b5fd4c. 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
Links to these hosts (documentation or services it may open):
github.com
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
Prompt Injection Test loads about 758 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 315 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from OWASP/secure-agent-playbook at commit 1b5fd4c, republished under its CC-BY-4.0 licence (© OWASP). 315 words, ~758 tokens.
Download SKILL.mdSave it as
.claude/skills/prompt-injection-test/SKILL.md (or your agent's skills folder).- name
- prompt-injection-test
- description
- Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy. Use when red-teaming AI apps, validating guardrails, or deepening LLM01 (Prompt Injection) assessments.
- license
- CC-BY-4.0
Prompt Injection Testing
Systematically test an LLM application's prompt injection defenses by following the full procedure in plays/prompt-injection-testing.md.
Based on the Arcanum PI Taxonomy by Jason Haddix (Arcanum Information Security). CC BY 4.0.
Steps
Scope and Input Surface Mapping — Identify all paths where attacker-controlled content reaches the LLM: direct (chat, API params) and indirect (file uploads, web fetches, RAG docs, tool outputs, MCP resources).
Test by Attack Intent (13 intents) — For each authorized intent, attempt to achieve the attacker's goal:
- INT-01 System Prompt Leak, INT-02 Jailbreak, INT-03 Tool Enumeration
- INT-04 API Enumeration, INT-05 Get Prompt Secret, INT-06 Attack Users
- INT-07 Data Poisoning, INT-08 Denial of Service, INT-09 Discuss Harm
- INT-10 Multi-Chain Attacks, INT-11 Generate Image, INT-12 Test Bias
- INT-13 Business Integrity
Test by Attack Technique (18 techniques) — Apply known payload construction methods:
- Framing, Narrative Smuggling, Cognitive Overload, Meta-Prompting
- Russian Doll, Memory Exploitation, Act as Interpreter, Contradiction
- End Sequences, Inversion, Rule Addition, Variable Expansion
- Link Injection, Puzzling, Anti-Harm Coercion, ASCII/Spatial
- Binary Streams, Spatial Byte Arrays
Apply Evasion Layers (20 evasions) — When techniques are blocked, retry with obfuscation:
- Encoding: base64, hex, morse, cipher, reverse
- Language: alt language, fictional language, phonetic substitution, emoji
- Structural: JSON/XML wrapping, markdown, metacharacter confusion, whitespace, splats
- Advanced: steganography, link smuggling, graph nodes, waveforms, case changing
Execute Test Matrix — Combine intents x techniques x evasions. Prioritize: high-impact intents first, indirect surfaces second, evasion sweeps against defenses that blocked direct attempts.
Assess Results — For each successful injection, document: severity, attack path (intent + technique + evasion + surface), exact payload, detection gap, and remediation.
Defense Validation — Check the 5-layer defense checklist: ecosystem hardening, model guardrails, prompt-layer defenses, data-layer controls, application-layer validation.
Output
Test results summary table (intent / technique / evasion / surface / result / severity), detailed findings using templates/finding.md, defense coverage checklist with gaps highlighted, and prioritized recommendations.
OWASP References
- LLM01: Prompt Injection
- LLM05: Improper Output Handling
- LLM06: Excessive Agency
- LLM07: System Prompt Leakage
© OWASP, CC-BY-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/ai-security-skills/skills/prompt-injection-test of OWASP/secure-agent-playbook.
Open the folder on GitHubat commit 1b5fd4c
Compare with similar skills
Prompt Injection Test 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 |
|---|---|---|---|---|---|---|
| Prompt Injection Test this skillOWASP/secure-agent-playbook | 187 | — | ~758 | Automated safety check: Pass | CC-BY-4.0 | |
| Skill Scannergetsentry/skills | 1k | 4 repos | ~2.5k | Automated safety check: Warn | Apache-2.0 | |
| Forensifyalexgreensh/repo-forensics | 188 | — | ~2.5k | Automated safety check: Notes | Custom licence | |
| Hol Guardhashgraph-online/hol-guard | 827 | — | ~542 | Automated safety check: Pass | Apache-2.0 | |
| Kesekit Checkcdppcorp/KESE-KIT | 361 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Setuphashgraph-online/hol-guard | 827 | — | ~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 OWASP/secure-agent-playbook
All 14 skills in this repoPrd Securability Enhancement
OWASP/secure-agent-playbook
Enhance PRDs, feature specs, user stories, or product briefs with explicit OWASP ASVS coverage and FIASSE v1.0.4 SSEM implementation guidance — before code is written.
Securability Engineering Review
OWASP/secure-agent-playbook
Score a codebase, file, or merge request against the FIASSE v1.0.4 SSEM model — 0-10 per attribute, equal-weighted pillars, evidence-backed strengths and weaknesses, prioritized recommendations…
Securability Engineering
OWASP/secure-agent-playbook
Generate, scaffold, or refactor code so it embodies FIASSE v1.0.4 SSEM qualities by default — 10 attributes, Transparency and Least-Astonishment principles, ASVS-aligned controls, defensive boundary…
Agent Security Audit
OWASP/secure-agent-playbook
Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails.
AI Security Verification
OWASP/secure-agent-playbook
Comprehensive AI security verification using OWASP AI Security Verification Standard (AISVS) framework.
API Security Review
OWASP/secure-agent-playbook
Comprehensive API security review against OWASP API Security Top 10 (2023).
Related
Categories
Questions about Prompt Injection Test
What does Prompt Injection Test do?
Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy. Prompt Injection Test is an agent skill from OWASP/secure-agent-playbook. Test LLM-integrated applications against known prompt injection techniques, evasion methods, and attack intents using the Arcanum PI Taxonomy.
When should I use Prompt Injection Test?
Prompt Injection Test fits situations like: red-teaming AI apps; validating guardrails; deepening LLM01 (Prompt Injection) assessments.
How do I install Prompt Injection Test in Claude Code?
Run `npx skills add OWASP/secure-agent-playbook --skill prompt-injection-test -a claude-code`. Or copy the skill folder (plugins/ai-security-skills/skills/prompt-injection-test in OWASP/secure-agent-playbook) into .claude/skills/prompt-injection-test in your project. Claude Code loads it when a task matches its description.
How do I install Prompt Injection Test in Codex?
Run `npx skills add OWASP/secure-agent-playbook --skill prompt-injection-test -a codex`. Or copy the skill folder (plugins/ai-security-skills/skills/prompt-injection-test in OWASP/secure-agent-playbook) into .agents/skills/prompt-injection-test in your project. Codex loads it when a task matches its description.
Can I use Prompt Injection Test 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 OWASP/secure-agent-playbook --skill prompt-injection-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prompt-injection-test, .gemini/skills/prompt-injection-test, .github/skills/prompt-injection-test and .opencode/skills/prompt-injection-test in your project.
What does Prompt Injection Test need to run?
SKILL.md names no scripts, command-line tools or credentials: Prompt Injection Test is instructions for the agent only.
Does Prompt Injection Test access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Prompt Injection Test 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 Prompt Injection Test use?
Prompt Injection Test is published under the CC-BY-4.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Prompt Injection Test use?
About 758 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Prompt Injection Test?
Skills that share tags, products or a category with Prompt Injection Test: Skill Scanner (getsentry/skills, 1k stars), Forensify (alexgreensh/repo-forensics, 188 stars), Hol Guard (hashgraph-online/hol-guard, 827 stars) and Kesekit Check (cdppcorp/KESE-KIT, 361 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prompt Injection Test?
OWASP (a GitHub organization) maintains it in OWASP/secure-agent-playbook, which has 187 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 25, 2026.
Source: OWASP/secure-agent-playbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.