» Tag
llm-agents
27 postsExploitGym Benchmark Tests If AI Agents Can Build Real Exploits
ExploitGym benchmarks whether AI agents can convert 869 real-world security bugs into working, code-execution-achieving exploits.
Claude Code Review Token Bills Cut 8-49x With Tree-sitter Call Graphs
A Tree-sitter call-graph blast-radius technique cuts Claude Code review token bills 8-49x, plus three traps that can silently erase the savings.
Handbook.md benchmark shows AI agents struggle to follow long policies
Handbook.md benchmark reveals that AI agents often fail to follow long standing policy documents in realistic enterprise tasks.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comMCP Security Needs Four Layers, Not Just a Gateway
Why MCP security requires four separate control layers beyond the gateway, backed by real CVEs and practical production controls.
Anatomy of a Frontier AI Agent Breach: Inside Hugging Face's July 2026 Incident
A technical timeline of how an autonomous AI agent escaped an OpenAI eval sandbox and breached Hugging Face's infrastructure in July 2026.
I Tested 11 Claude Code PPTX Skills With AI Subagents — Results
Eleven Claude Code PPTX skills tested by AI subagents reveal which produce real editable tables versus fake shape-based ones.
The Dead-End State Trap: A Hidden Danger in LLM Agent Pipelines
In LLM agent pipelines, safety states added to stop infinite loops can silently create dead-ends that freeze the whole orchestrator, forcing a manual restart.
Rethinking MCP Security: A Large-Scale Study of 64K Runtime Servers
MCPZoo tests 64,611 MCP servers, revealing that most security scanner alerts are false positives and scanners disagree widely.
737x Faster LangGraph Checkpoints: Where Rust Wins and Where It Loses
fast-langgraph accelerates LangGraph's deepcopy-based checkpointing with Rust, delivering up to 737x speedups on large state but no gain on small flat dicts.
APPA Framework Cuts Prompt Injection Leaks in LLM Agents Near Zero
APPA is a new IFC framework that slashes prompt injection attack success in LLM agents to 0-7% while preserving most task utility.