hunt-llm-ai
Skill0 starsChanged 5 months agoNo licenceView on GitHub
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use, ASCII smuggling, agentic AI security framework (ASI01-ASI10). Patterns: direct prompt injection in user input (bypass system prompt with 'ignore previous instructions'), indirect injection via documents/web pages the model reads, ASCII smuggling (Unicode tag block U+E0000-U+E007F invisible to humans, visible to model), tool-use exfiltration (model has fetch_url tool, attacker injects URL, model exfils chat history), system prompt extraction (manipulate model to reveal hidden instructions), training data extraction, IDOR-via-AI (model reads other-user data via system prompt confusion). Tools: chatbots, RAG endpoints, summarization, agentic copilots. Detection: any LLM-backed endpoint, document upload that triggers AI processing, autonomous agent with tools. Validate: cross-user data leak, system prompt revealed, tool-use exfil demonstrated. Use when hunting AI features, chatbots, RAG, agentic systems.
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- elementalsouls/Claude-BugHunter★ 5.4ksame name
- Kur1sulab/blackbox★ 3same name
- ajtazer/heckit★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository50 other files it gives its agents.
- apk-redteam-pipelineSkill
- bb-local-toolkitSkill
- bb-methodologySkill
- bug-bountySkill
- bugcrowd-reportingSkill
- cloud-iam-deepSkill
- enterprise-vpn-attackSkill
- evidence-hygieneSkill
- hunt-api-misconfigSkill
- hunt-aspnetSkill
- hunt-atoSkill
- hunt-auth-bypassSkill
- hunt-business-logicSkill
- hunt-cache-poisonSkill
- hunt-cloud-misconfigSkill
- hunt-csrfSkill
- hunt-dispatchSkill
- hunt-file-uploadSkill
- hunt-graphqlSkill
- hunt-http-smugglingSkill
- hunt-idorSkill
- hunt-mfa-bypassSkill
- hunt-miscSkill
- hunt-ntlm-infoSkill
- hunt-oauthSkill
- hunt-race-conditionSkill
- hunt-rceSkill
- hunt-samlSkill
- hunt-sharepointSkill
- hunt-sqliSkill
- hunt-ssrfSkill
- hunt-sstiSkill
- hunt-subdomainSkill
- hunt-xssSkill
- hunt-xxeSkill
- m365-entra-attackSkill
- meme-coin-auditSkill
- mid-engagement-ir-detectionSkill
- offensive-osintSkill
- okta-attackSkill
- osint-methodologySkill
- redteam-mindsetSkill
- redteam-report-templateSkill
- report-writingSkill
- security-arsenalSkill
- supply-chain-attack-reconSkill
- triage-validationSkill
- vmware-vcenter-attackSkill
- web2-reconSkill
- web3-auditSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.