aig-scannerA.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard. Us...
Install via ClawdBot CLI:
clawdbot install aigsec/aig-scannerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/Tencent/AI-Infra-Guard/Uses known external API (expected, informational)
api.openai.comAudited Apr 17, 2026 · audit v1.0
Generated May 6, 2026
Security teams scan AI infrastructure services (e.g., model serving endpoints, vector databases) on local or private networks for known vulnerabilities using A.I.G's built-in scanner. This automates CVE checks for common AI infra components.
Organizations audit third-party MCP servers or AI tool repositories for security flaws before integration. The scanner evaluates GitHub repos or local skill directories for code vulnerabilities and misconfigurations.
Companies with deployed AI agents scan agent configurations stored in A.I.G for unsafe permissions or data exposure. This ensures agent settings adhere to security policies before production use.
Red teams assess LLM deployments for jailbreak susceptibility by submitting adversarial prompts and analyzing responses. The skill automates evaluation using configurable target and evaluation models.
After submitting a scan, users retrieve results with optional polling. This supports periodic re-checks of infrastructure or tools, integrating into CI/CD pipelines for ongoing security assurance.
Offer recurring AI infrastructure and tool security scans as a service to enterprise clients. Revenue is generated through monthly or annual subscription fees based on scan frequency and asset count.
Provide LLM jailbreak evaluation and comprehensive AI security audits as a standalone service for clients preparing for production deployment. Revenue comes from per-engagement consulting fees.
Package the scanner as a plugin for AI orchestration platforms (e.g., OpenClaw) and charge a licensing fee per deployment or per scan. Revenue includes license sales and optional support contracts.
💬 Integration Tip
Configure AIG_BASE_URL and optional AIG_API_KEY environment variables, then use the provided aig_client.py script via exec for all scan operations.
Scored May 6, 2026
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
Collaborative thinking partner for exploring complex problems through questioning
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.