Radar / AI security / leanrea
leanrea: an 8 KB agent skill that replaces the REA reverse-engineering MCP stack
A single 8 KB SKILL.md that teaches coding agents to reverse-engineer apps with plain CLI tools (nm, otool, jadx, binwalk, sqlite3) instead of REA's 207-tool MCP server.
Why it matters
Benchmarked 38% faster and 35% cheaper than the REA MCP layer at equal accuracy - a concrete data point in the growing debate over MCP bloat versus plain-CLI agent skills.
What you could build with it
A security consultancy or indie developer could offer overnight binary teardown audits of client software: point an agent armed with this skill at an app and get an evidence-backed report tracing features back to code for compliance or acquisition due diligence.
Does it hold up?
Too early to judge: the README publishes a solid head-to-head benchmark (74/75 vs REA's 75/75 at 35% lower cost), but no independent users have reported results yet and the benchmark covers only macOS CLI tooling.
Learn more
First spotted on github: source.
More AI security
iFixAi: independent auditing of AI agentsIndependent AI-agent auditor: 250+ inspections across 69 misalignment categories (red teaming + operational assurance)…security · JEV 0.76OpenAI, Anthropic and Google DeepMind jointly unveil cyber-focused safety models and safeguardsThe three rival labs disclosed weeks of behind-the-scenes coordination and jointly released a set of cyber-focused AI…security · JEV 0.73OpenAI textGrain watermarking for ChatGPT and Codex in the EUOpenAI will roll out its invisible textGrain watermarking system to ChatGPT/Codex users in the EU over the coming…security · JEV 0.65Cloudflare security-audit-skill: multi-phase security audits for coding agentsA coding-agent skill that runs multi-phase security audits with independently verified, machine-checkable findings.security · JEV 0.63LiveNerf: a pre-registered benchmark for post-release model driftOpen-source, pre-registered 30-day benchmark that detects whether Claude Opus 5.5 quietly gets worse after launch.security · JEV 0.61Sandlock 0.8.8: deferred commit for agent sandboxesThe process-based Linux AI sandbox (no container, no VM) ships deferred commit: every run returns a changeset of what…security · JEV 0.58
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.