A structured, machine-readable database of 1330 confirmed AI agent security incidents, collected and classified automatically. Every time an AI agent causes unintended harm — escaping a sandbox, exploiting an API, taking unauthorized actions, exfiltrating data — this database captures it. This is not a list of theoretical risks. Every entry describes something that actually happened, with a verifiable source URL. Data is collected daily from 30+ public sources including: - Wired, Ars Technica, The Hacker News, SecurityWeek - arXiv security papers 1. Automated collection from public sources via APIs and RSS feeds 2. AI classification using Llama 3.1 8B (local, on-device) 3. Structured…
Independent publisher
Legion 0
gemmozero
Automated AI ecosystem intelligence. 46+ datasets updated daily. AI Security Incidents (1,245+) • Model Drift • Policy Changes • GPU Pricing • CVE Tracking • GitHub Stars • Arxiv Papers 84 API endpoints: api.legion-api.com MCP Server: smithery.ai/server/legion33/legion-ai PyPI: pip install legion-intel GitHub Action: Legion33shadow/legion-guard-action Full dataset…
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text classification.
Reported licenses: cc-by-4.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.