hunt-llm-ai
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model), tool-use exfiltration (model has fetch/browse tool, attacker injects OOB URL, model exfils chat history/secrets), markdown-image zero-click exfil, system-prompt extraction, IDOR-via-AI (cross-tenant data). Targets: chatbots, RAG, summarizers, agentic copilots, MCP tools. Detection: any LLM-backed endpoint, doc upload triggering AI processing, autonomous agent with tools. Validate: OOB/Collaborator callback for exfil, verbatim-reproducible system-prompt leak (run twice), verifiable cross-tenant leak or RCE. Confabulation is NOT a finding. Use when hunting AI features, chatbots, RAG, agentic systems, MCP.
SRC Publisher-stated: these are the publisher's own words, not an assessment.
Key facts
- Type
- Agent skill · skill-mdSRC
- Publisher
- elementalsouls · individualSRC
- Licence
- MITSRC
- Open source
- YesDER
- Hosting
- Local (runs on your machine)SRC
- Latest version
- Unknown
- Languages
- pythonSRC
- First published
- Unknown
- In this catalogue since
- DER
- Last verified
- Not verified by a researcher. Last seen in a source on 2026-11-21.
Capabilities and categories
Assigned by keyword rules from the description unless marked otherwise. The matched word is shown so you can judge the match.
| Capability | Evidence | Kind |
|---|---|---|
| Agent Threat Protection | matched prompt injection | DER |
| matched | DER | |
| Retrieval-Augmented Generation | matched rag | DER |
| Multi-provider Access | matched any llm | DER |
| Prompt Injection Defense | matched prompt injection | DER |
| Security Review | matched owasp | DER |
Filed underAgent InfrastructureData & KnowledgeDeveloper ToolsProductivity & CollaborationAI Coding AgentsAgent SecurityCommunication & MessagingModels & GatewaysRetrieval & RAGCode ReviewModel Gateways & Routing
Integrations DER
No third-party service is named in the description or package metadata.
Platform compatibility
No pairing has been tested by AgentSidekick. Each status says what kind of evidence exists, not whether it works for you.
Protocol-level26
Each platform listed officially documents support for the Agent Skills format. This specific pairing has not been tested.
Platform discontinued1
| Platform | Basis |
|---|---|
| Roo CodeDiscontinued | Roo Code documented support for the Agent Skills format but is discontinued. Project shut down and repository archived. |
Unknown20
Could not confirm whether Each platform listed supports the Agent Skills format.
Install
Read from registry metadata. Follow the publisher's instructions; we have not run this.
No machine-readable install metadata is on record. The publisher's instructions are at the install page.
Permissions and signals
Signals, not a safety verdict. They describe what the product's metadata references. Security review: not reviewed.
No signals collected
Automated inspection found nothing to report, or there was no metadata to inspect. That is not evidence of safety.
Known advisories for the published package SRC
An advisory existing does not mean the listed version is affected: compare the vulnerable range with the version you install. None found is not evidence of safety.
No advisories found
No published advisory matches a package this product declares. Products without a declared package cannot be matched at all. This is not evidence of safety.
Evaluation
Separate dimensions, each with its evidence. There is no overall score: the dimensions do not add up to one number honestly.
- Source authority
Publisher-listed
Listed by the publisher in a source it controls (SKILL.md file, plugin marketplace manifest or extension registry). Field values are the publisher's own claims.
- Publisher verification
Not verified
No publisher identity check is available for this source.
- Maintenance activity
Active
Last push 2026-11-21 (0 days before this page was built).
- Licence clarity
MIT
Licence identifier as reported by GitHub repository metadata.
- Installation clarity
Linked
An install or documentation link is available; steps are not machine-readable.
- Documentation
Repository / website only
No dedicated documentation URL on record. AgentSidekick has not assessed documentation quality.
- Compatibility evidence
Protocol-level only
Compatibility is inferred from the standard it implements. No pairing has been tested.
- Security review
Not reviewed
AgentSidekick has not audited this product. No automated signals were collected. That is not evidence of safety.
Pricing
Not published in any source we track. The code is open source, which says nothing about the cost of any hosted service.
Repository activity
elementalsouls/claude-bughunter (subfolder skills/hunt-llm-ai; figures are for the whole repository). Read from the GitHub API on 2026-11-21.
Version history SRC
No version list is published in any source we track.
Change history
What changed between two ingests of the same source, and when the product was first seen. Registry releases are under Version history.
- First seen
Competitors and alternativesDER
Paired by shared capabilities and integrations. Similar on paper; not tested side by side.
Direct
Same type, overlapping capabilities.
Agent skillby Orchestra-ResearchSRC
SharesAgent Threat ProtectionPrompt Injection DefenseRetrieval-Augmented Generation
Adjacent
A different form or a partial overlap.
MCP serverby radmail.aiSRC
SharesAgent Threat ProtectionPrompt Injection DefenseEmail
MCP serverby bawbelSRC
SharesSecurity ReviewAgent Threat ProtectionPrompt Injection Defense
MCP serverby bawbelSRC
SharesSecurity ReviewAgent Threat ProtectionPrompt Injection Defense
MCP serverby KeyValueSoftwareSystemsHEU
SharesSecurity ReviewAgent Threat ProtectionPrompt Injection Defense
MCP serverby OWASPHEU
SharesSecurity ReviewAgent Threat ProtectionPrompt Injection DefenseRetrieval-Augmented Generation
MCP serverby cgrtmlSRC
SharesSecurity ReviewAgent Threat ProtectionPrompt Injection Defense
Provenance
Which source set each field, what kind of claim it is, and when.
| Field | Source | Kind | Set on |
|---|---|---|---|
| Canonical URL | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Publisher | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Description | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Hosting | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Install link | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Integration type | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Languages | GitHub repository metadata | SRC | 2026-11-21 |
| Licence | GitHub repository metadata | SRC | 2026-11-21 |
| Name | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Open source | GitHub repository metadata | DER | 2026-11-21 |
| Type | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Repository | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
| Source URL | SKILL.md files in public GitHub repos | SRC | 2026-11-21 |
Sources
- SKILL.md files in public GitHub repos: github.com (external)checked
Not verified by a researcher. Last seen in a source on . Report incorrect information