Individual skill
testing-llm-prompt-injection-and-jailbreaks
Testing LLM-backed applications, chatbots, and AI agents for direct and indirect prompt injection, jailbreaks, system-prompt leakage, and tool/agent abuse during authorized penetration tests, using structured payload families and reliable confirmation signals.
internal/tools/skills/data/ai-security/testing-llm-prompt-injection-and-jailbreaks/SKILL.md
Source commit d42f381ad34843e71a42658e5c57290c713e85af
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Instructions only
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,318
- Repository last updated
- Nov 8, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- cybersecurity Repository topic
- security Repository topic
- bug-bounty Repository topic
- automation Repository topic
- autonomous-pentesting Repository topic
- ai-agent Repository topic
- ai-security Repository topic
- ethical-hacking Repository topic
- golang Repository topic
- penetration-testing Repository topic
- ai-security Declared skill tag
- prompt-injection Declared skill tag
- penetration-testing Declared skill tag
- security Derived category
- testing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# Testing LLM Prompt Injection and Jailbreaks
## When to Use
- During authorized assessments of chatbots, copilots, RAG systems, and autonomous AI agents
- When the application mixes a trusted system prompt with untrusted user input or external content
- When the LLM consumes attacker-influencable data (web pages, emails, files, repo issues, tool output)
- When the model can call tools/functions or take actions (send email, run code, open PRs)
- When validating system-prompt confidentiality, content guardrails, and output handling
## Prerequisites
- **Authorization**: Written agreement covering the AI application and any connected tools/data
- **Burp Suite / HTTP client**: To reach chat/completions endpoints and replay payloads