Orca AI Incident Archive

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

Open database of publicly disclosed AI agent security incidents since January 2025 (prompt injection, exploited MCP servers, poisoned agent packages, agents deleting production data): one Markdown record per event with an attack-chain diagram, primary sources and a confirmed-victim flag, plus JSON/CSV exports

HTML No licence declared

View on GitHub → Find it in the atlas

Install

git clone https://github.com/Continuum-AI-Corp/Orca-AI-Incident-Archive.git

Repository reader

Explore before you clone

Read the project’s README, skills and supporting Markdown here. Rendered view is shown first; source is one click away when you need the exact text.

Fetched from GitHub
Open on GitHub
Loading the project’s README…

Public files are loaded on demand from the repository. The atlas does not copy or modify them.

Screenshot

Screenshot or social card for Orca AI Incident Archive
GitHub's social card — no screenshot was found for this project, fetched from source rather than copied into this repository.

Platform support

Derived from the project's own README, install route, CI configuration and release assets — not from running it.
PlatformRuns hereOn what evidence
WindowsNoNo evidence of support anywhere in the project.
WSL2NoNo evidence of support anywhere in the project.
macOSNoNo evidence of support anywhere in the project.
LinuxNoNo evidence of support anywhere in the project.
DockerNoNo evidence of support anywhere in the project.

Where it came from

Named by 2 of the 39 lists the atlas merges, independently of each other.

  • AI Agents (Jenqyang)
  • Agent Skill Security

How it is classified

One topic, 1 harness. Each link is a prerendered page of everything else in that slice.

Observability & EvalsMCP

Related in Observability & Evals

Closest first — projects that plug into the same harnesses, then the ones the most lists agreed on.

  • Codeburngetagentseal/codeburnFree, local tool that tracks AI coding token usage and cost across 31 tools and agents by model, project, and task. Worth including because…
  • Opikcomet-ml/opikComet's open-source AI observability and evaluation platform: deep tracing of LLM calls, conversation logging, and agent activity, plus built-in…
  • EvalViewhidai25/eval-viewRegression testing for AI agents. Snapshot behavior, detect tool-call and output regressions, with golden-baseline diffing and LLM-as-judge scoring…
  • tailtestavansaber/tailtestAutomatically generates and runs tests for every file Claude Code creates or modifies. PostToolUse hook detects changes, generates test scenarios…
  • Accio-org/RealReplicaBenchAccio-org/CommerceAgentBenchAlibaba International's benchmark for long-horizon agents in high-fidelity, stateful replicas of real online services: 107 tasks spanning CLI…
  • AEGISantropos17/AegisWindows-first desktop monitor for local agent processes, configured file activity, TCP endpoints and audit exports. Useful for inspecting a…
  • BitRouterbitrouter/bitrouterAgent-native LLM router that optimizes your agent with every run — zero harness changes, with every model call reliable, traceable, secure, and…
  • CC Harnesslookfree/cc-harnessby lookfree - Desktop workbench that reads Claude Code session files locally and renders the subagent and workflow topology as a live graph, with…