Individual skill
ai-threat-testing
Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats.
skills/ai-threat-testing/SKILL.md
Source commit 95fdc128af4ca1ae16b3226f9430f1bad97b0656
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 5, 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)
- 610
- Repository last updated
- Jul 29, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- bounty-hunters Repository topic
- hackerone Repository topic
- pentest Repository topic
- pentest-tool Repository topic
- security Repository topic
- security-research Repository topic
- security-tools Repository topic
- security Derived category
- operations Derived category
- data Derived category
- testing Derived category
- security-application Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 4,876 bytesreference/adversarial-pixel-attacks.mddoc · 5,439 bytesreference/agentic-tool-hijacking.mddoc · 7,417 bytesreference/catalog/llm-top10-2025.jsonasset · 6,648 bytesreference/gradient-leakage-attacks.mddoc · 5,529 bytesreference/hopfield-recovery.mddoc · 4,723 bytesreference/llm01-prompt-injection.mddoc · 3,474 bytesreference/llm02-insecure-output.mddoc · 2,959 bytesreference/llm03-training-poisoning.mddoc · 3,476 bytesreference/llm04-resource-exhaustion.mddoc · 3,052 bytesreference/llm05-supply-chain.mddoc · 4,062 bytesreference/llm06-excessive-agency.mddoc · 4,100 bytesreference/llm07-model-extraction.mddoc · 4,246 bytesreference/llm08-vector-poisoning.mddoc · 4,000 bytesreference/llm09-overreliance.mddoc · 4,206 bytesreference/llm10-logging-bypass.mddoc · 4,708 bytesreference/malicious-keras-model-triage.mddoc · 5,117 bytesreference/scenarios/llm/llm01-prompt-injection-direct.mddoc · 3,716 bytesreference/scenarios/llm/llm01-prompt-injection-indirect.mddoc · 3,862 bytesreference/scenarios/llm/llm02-insecure-output-handling.mddoc · 3,772 bytesreference/scenarios/llm/llm03-training-data-poisoning.mddoc · 3,924 bytesreference/scenarios/llm/llm04-denial-of-service.mddoc · 4,023 bytesreference/scenarios/llm/llm05-supply-chain-vulnerabilities.mddoc · 5,921 bytesreference/scenarios/llm/llm06-sensitive-info-disclosure.mddoc · 3,727 bytesreference/scenarios/llm/llm07-insecure-plugin-design.mddoc · 3,930 bytesreference/scenarios/llm/llm08-excessive-agency.mddoc · 3,661 bytes
Read excerpt
# AI Threat Testing
Test LLM applications for OWASP LLM Top 10 vulnerabilities using 10 specialized agents. Use for authorized AI security assessments.
## Quick Start
```
1. Specify target (LLM app URL, API endpoint, or local model)
2. Select scope: Full OWASP Top 10 | Specific vulnerability | Supply chain
3. Agents deploy, test, capture evidence
4. Professional report with PoCs generated
```
## Coverage — OWASP LLM Top 10, 2025 edition