Trending Repos
TrendingRisersNewestTopicsCollectionsCompare
TrendingRisersNewestTopicsCollectionsCompare
Trending Repos

Trending Repos tracks GitHub momentum from stars, forks, and rank history.

Explore

TrendingRisersNewestTopicsCollections

Tools

SearchCompareBadgesSubmit a repo

Project

AboutStatsDevelopersContactPrivacy
Back to trending
HeadyZhang/agent-audit avatar

HeadyZhang/agent-audit

GitHub

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.

Python192 stars22 forksMIT
ai-agentai-securityai-security-toolclicrewailangchainlangchain-security-llm-safetyllm-securitymcpowaspprompt-injectionpythonsecuritystatic-analysistaint-analysisvulnerability-detectionvulnerability-scanner

Momentum

HeadyZhang/agent-audit has 192 GitHub stars. It gained 0 stars over 1 recorded day in the last 7 days (snapshots through Jul 4, 2026).

It currently ranks #38723 daily, #38864 weekly, #39819 monthly by momentum on Trending Repos; its best-ever rank is #4851.

Trending Repos first recorded it on Jul 3, 2026.

Rankings

PeriodRankScore
Daily
#387230.0
Weekly
#388640.0
Monthly
#398190.0
How scoring works

Engagement

Total stars
Daily new stars
Recent daily star gains
DateStars gainedTotal starsForks gained
Jul 4, 202601920

Similar trending repositories

  • morluto/reaReverse engineer anything with agents, from app behavior down to native binaries.TypeScript450,914 stars#1 this week
  • sherlock-project/sherlockHunt down social media accounts by username across social networksPython109,496 stars#3 this week
  • vercel-labs/agent-desktopComputer use CLI for AI agentsRust21,631 stars#13 this week
  • D4Vinci/Scrapling🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_devPython101,329 stars#24 this week
  • qybaihe/bla🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust -> Hallucinate.TypeScript5,145 stars#42 this week
  • ccch1mneyyy/dsh-Godsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。Dart19,101 stars#7 this week

Embeds

Best rank #4851
HeadyZhang/agent-audit badge
Markdown