incident-database

Here are 7 public repositories matching this topic...

Continuum-AI-Corp / Orca-AI-Incident-Archive

An open database of real-world AI agent incidents.

Updated Oct 5, 2026
HTML

mars2021y-gif / autonomous-ai-agent-security-incidents-2026

Autonomous AI Agent Security Incidents of 2026: Benchmark dataset (109 incidents), falsification matrix, 2-page executive summary, and multi-agent privilege attenuation harness (100% EPR).

benchmark dataset cybersecurity zenodo autonomous-agents ai-safety docker-security sandbox-escape vulnerability-research ai-security huggingface confused-deputy incident-database

Updated Oct 6, 2026
Python

ai-solutions-sk / stupidllm-incidents

Star

Documented AI coding agent failures — severity-scored, source-verified, CC BY 4.0. Callable over MCP.

mcp open-data dataset cve ai-safety ai-agents llm coding-agents incident-database

Updated Sep 11, 2026

vdalal / ARE-Incident-Database

Star

The ARE Incident Database: an OWASP-ASI-indexed registry of real agent failures, with honest coverage boundaries.

owasp dataset ai-safety ai-agents ai-security prompt-injection llm-security agentic-security agent-reliability-engineering incident-database

Updated Sep 15, 2026
Python

piperoll / registry

Star

PipeRoll - Agent Incident Registry: verified public records of AI-agent failures. Open data, open submissions, verified registration.

registry open-data dataset ai-safety ai-agents agent-economy ai-incidents incident-database

Updated Oct 5, 2026
Python

AaronVick / AGENT_FABLES

Star

Machine-readable preflight for software agents: pass the next unsent tool call; receive ≤2 revision-pinned failure cards or typed UNKNOWN. Offline/zero-install; never authorizes execution.

offline-first mcp zero-install security-advisories ai-agents preflight machine-readable llm-security function-calling agent-tools agentic-ai tool-calling ai-agent-security agent-safety agent-guardrails incident-database devops-safety destructive-operations

Updated Aug 16, 2026
JavaScript

basitalisandhu / ai-agent-incidents

Star

Open dataset of AI agent and LLM security incidents (2023 to 2026): schema-validated JSON records of prompt injection, data exfiltration, supply-chain and agent-misuse events, coded by the role AI plays and mapped to the OWASP LLM and Agentic Top 10 and MITRE ATLAS. JSON, CSV, RSS and a searchable site. Data CC BY 4.0.

json-schema mcp owasp open-data dataset security-incidents hacktoberfest ai-safety threat-intelligence ai-agents security-research ai-security mitre-atlas prompt-injection llm-security agentic-ai agent-security ai-incidents incident-database

Updated Oct 5, 2026
HTML

Add this topic to your repo

To associate your repository with the incident-database topic, visit your repo's landing page and select "manage topics."

Learn more