AI-Infra-Guard by Tencent Zhuque Lab

v4.1.8 Bugfix

This release fixes issues for SREs watching stability and regressions.

Published 21d Offensive & Pentesting

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent agent-security ai-infra ai-red-teaming ai-security llm

+13 more

llm-evaluation llm-jailbreak llm-security mcp-scan openclaw-security prompt-injection prompt-security scanner security security-tools skill-scanner skills-security vulnerability

ReleasePort's take

Light signal

editorial:auto 13d

Release v4.1.8 of AI-Infra-Guard makes tool name lookup case-insensitive and cleans up vulnerability rule duplicates.

Why it matters: Patch to v4.1.8 immediately to enable case‑insensitive tool lookups and eliminate 143 duplicate GHSA files that could cause false positives in scans.

Summary

AI summary

Fixed tool name lookup to be case‑insensitive.

Changes in this release

Type	Severity	Summary	CVE
Security	Medium	Remove 143 duplicate GHSA files with CVE references Remove 143 duplicate GHSA files with CVE references Source: llm_adapter@2026-05-21 Confidence: high	—
Feature
Feature	Medium	Add invitation code application link to all README files Add invitation code application link to all README files Source: llm_adapter@2026-05-21 Confidence: high	—
Feature	Medium	Add 1 new related paper to README and fix ZH PDF links Add 1 new related paper to README and fix ZH PDF links Source: llm_adapter@2026-05-21 Confidence: high	—
Feature	Medium	Add team introduction, core members, and papers section across all READMEs Add team introduction, core members, and papers section across all READMEs Source: llm_adapter@2026-05-21 Confidence: high	—
Feature	Medium	Update component count 58→64 and vuln stats 1200+→1300+ across all 9 README languages Update component count 58→64 and vuln stats 1200+→1300+ across all 9 README languages Source: llm_adapter@2026-05-21 Confidence: high	—
Bugfix	Medium	Make tool name lookup case-insensitive Make tool name lookup case-insensitive Source: llm_adapter@2026-05-21 Confidence: high	—
Bugfix	Medium	Remove invalid fingerprints (chatgpt-mcp-server/pptagent) and fix GHSA-9p3r YAML format Remove invalid fingerprints (chatgpt-mcp-server/pptagent) and fix GHSA-9p3r YAML format Source: llm_adapter@2026-05-21 Confidence: high	—
Refactor	Low	Restore GHSA files added upstream after base commit Restore GHSA files added upstream after base commit Source: granite4.1:30b@2026-05-22-audit Confidence: low	—

Full changelog

[v4.1.8] - 2026-05-14

Fixed

Tools: Make tool name lookup case-insensitive (2e76c7d)
Vuln Rules: Remove 143 duplicate GHSA files that have corresponding CVE references (bf06029)
Vuln Rules: Remove invalid fingerprints (chatgpt-mcp-server/pptagent), fix GHSA-9p3r YAML format (8a19ff8)
Vuln Rules: Restore GHSA files added upstream after base commit (6cdecfd)

Changed

Docs: Add invitation code application link to all README files (08c356a)
Docs: Add 1 new related paper to README + fix ZH PDF links (2cbc750)
Docs: Add team introduction, core members, and papers section across all READMEs (3ef3cb8)
Docs: Update component count 58→64 and vuln stats 1200+→1300+ across all 9 README languages (0a3b50b)

Contributors

Special thanks to @feiyang666, @zhuque, @boyhack, @aigsec, @aig-doc-bot, @jucie-pie, @AIG-Bot

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track AI-Infra-Guard by Tencent Zhuque Lab

Get notified when new releases ship.

About AI-Infra-Guard by Tencent Zhuque Lab

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

All releases →