prompt-injection-test
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.
- Installs
- 169
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/owasp/secure-agent-playbook --skill prompt-injection-test- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads prompt-injection-test automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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
FAQ
What does the prompt-injection-test skill do?
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.
How do I install prompt-injection-test?
Run npx skills add https://github.com/owasp/secure-agent-playbook --skill prompt-injection-test in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/prompt-injection-test/ (personal) or .claude/skills/prompt-injection-test/ (project).
Which AI agents can use prompt-injection-test?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is prompt-injection-test safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains prompt-injection-test?
It is published by owasp in owasp/secure-agent-playbook. It has 169 recorded installs.
More from owasp/secure-agent-playbook
web-security-review
owasp/secure-agent-playbook
Review web applications against the OWASP Top 10 for Web Applications (2021). Use when auditing web apps, reviewing server-side code, or assessing web frameworks for the classic OWASP Top 10 risks including injection, broken auth, and XSS.
api-security-review
owasp/secure-agent-playbook
Comprehensive API security review against OWASP API Security Top 10 (2023). Use when reviewing OpenAPI/Swagger specs, auditing REST/GraphQL/gRPC implementations, testing authentication mechanisms, or checking API gateway configurations. Covers BOLA/IDOR, broken auth, mass assignment, rate limiting, SSRF, and more with real-world attack scenarios.
code-review-security
owasp/secure-agent-playbook
Security-focused code review mapped to OWASP Top 10 and ASVS. Use when reviewing pull requests, auditing files or modules for vulnerabilities, or performing pre-merge security gate checks. Covers injection, auth, authorization, cryptography, data exposure, misconfiguration, and deserialization.
security-guidance
owasp/secure-agent-playbook
Security-first development guidance based on OWASP ASVS (Application Security Verification Standard). Use this skill automatically when planning or implementing any code that touches user input, authentication, data persistence, network communication, file I/O, cryptography, or access control. This skill ensures all generated code adheres to industry-standard security practices with explicit references to applied guidance.
secrets-scan
owasp/secure-agent-playbook
Detect hardcoded credentials, API keys, tokens, and secrets in source code and configuration files. Use when reviewing code for leaked secrets before commit/merge, auditing a repository for credential exposure, or setting up secret detection.
sca-audit
owasp/secure-agent-playbook
Scan project dependencies for known vulnerabilities (CVEs). Use when reviewing dependency files (package.json, requirements.txt, go.mod, pom.xml, Gemfile, Cargo.toml, etc.), triaging Dependabot/Renovate alerts, or performing pre-deployment security checks.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available