{{ message }}
Repository navigation
GenAI plan: add Orca AI Incident Archive to agentic AI resources - #41
Open
xizhuomengcontin wants to merge 1 commit into
Open
xizhuomengcontin wants to merge 1 commit into
xizhuomengcontin wants to merge 1 commit into
Conversation
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
mail2ncsekhar
approved these changes
Oct 10, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds the Orca AI Incident Archive to the GenAI Security Study Plan, at the end of Additional Resources → 7. Agentic AI, AI Agents & MCP Security.
The plan's Agentic AI week asks the reader to "Analyze case studies of agentic AI failures" but doesn't point to a source for them, and this archive is one. It has 393 records since late 2024: incidents, vulnerabilities, research, threat reports and policy. Each record links to its public sources and is graded for source quality. Each record also says whether harm was confirmed or only demonstrated, which matters for the case-study exercise. A coding agent wiping a production database is not the same as a proof-of-concept prompt injection. Many records map onto the ASI risks the plan already covers: goal hijack via indirect prompt injection, agentic supply chain (malicious skills, poisoned extensions), and rogue actions.
Disclosure: I'm on the team that maintains it. It's new (September 2026) and has few stars, and severity is our editorial call. You merged it into awesome-genai-security earlier; this study plan is a separate place where it seemed useful. Happy to reword or move it.
🤖 Generated with Claude Code