AI-Infra-Guard by Tencent Zhuque Lab

v4.1.9 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 14d 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

Affected surfaces

auth rbac

ReleasePort's take

Light signal

editorial:auto 13d

AI-Infra-Guard v4.1.9 adds 26 prompt injection attack operators (20+ single-turn, 6 multi-turn) and indirect injection defense for scanning agents.

Why it matters: New multi-turn operators expand injection detection coverage. Evaluate in dev if your workloads use untrusted inputs with LLM chains.

Summary

AI summary

Updates v4.1.9] - 2026-05-21, fbac88b..14a3d01, and f4e7cd8..6116a8a across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Add 20+ single-turn attack operators for Prompt Security. Add 20+ single-turn attack operators for Prompt Security. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: high	—
Feature	Medium	Add 6 multi-turn attack operators for Prompt Security. Add 6 multi-turn attack operators for Prompt Security. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: high	—
Feature	Medium	Register and document newly added attack operators in Prompt Security. Register and document newly added attack operators in Prompt Security. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: high	—
Feature	Medium	Add indirect prompt injection defense to scanning agent prompts. Add indirect prompt injection defense to scanning agent prompts. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: high	—
Other
Other	Medium	Reorder academic citation papers by publication date descending. Reorder academic citation papers by publication date descending. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: low	—
Other	Medium	Normalize quotes in DE/RU paper citations to standard format. Normalize quotes in DE/RU paper citations to standard format. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: low	—
Other	Medium	Simplify overly formal acknowledgement wording across all languages. Simplify overly formal acknowledgement wording across all languages. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: low	—
Other	Medium	Add Changan Auto and HUST logos to user appreciation section. Add Changan Auto and HUST logos to user appreciation section. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: low	—
Other	Medium	Sync HUST and Nankai University logo heights (45px) across all READMEs. Sync HUST and Nankai University logo heights (45px) across all READMEs. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: low	—
Other	Medium	Add 1 new related paper to README. Add 1 new related paper to README. Source: granite4.1:8b-q6_K@2026-05-21 Confidence: low	—

Full changelog

[v4.1.9] - 2026-05-21

Added

Prompt Security: Add 20+ single-turn attack operators (invisible-text, case-formatting, script-system, unicode-style, classical-cipher, classic-encoding, SystemOverride, SuperUser, LinguisticConfusion, Roleplay, PromptProbing, PromptInjection, PROMISQROUTE, PermissionEscalation, Multilingual, MathProblem, InputBypass, ICRTJailbreak, GrayBox, GoalRedirection, EquaCode, ContextPoisoning) (fbac88b..14a3d01)
Prompt Security: Add 6 multi-turn attack operators (TreeJailbreaking, SequentialJailbreak, LinearJailbreaking, CrescendoJailbreaking, BestofN, BadLikertJudge) (f4e7cd8..6116a8a)
Prompt Security: Register and document newly added attack operators (03d67de, ce3869c)
Scan: Add indirect prompt injection defense to scanning agent prompts (bce80c9)

Changed

Docs: Reorder academic citation papers by publication date descending (0ae8625)
Docs: Normalize quotes in DE/RU paper citations to standard format (b9b4d2b)
Docs: Simplify overly formal acknowledgement wording across all languages (5926ade)
Docs: Add Changan Auto and HUST logos to user appreciation section (968710f)
Docs: Sync HUST and Nankai University logo heights (45px) across all READMEs (7ef9cd4, c59eb29)
Docs: Add 1 new related paper to README (b93e1e0)

Contributors

Special thanks to @y3oZ, @Truman, @zhuque, @boyhack, @aigsec, @aig-doc-bot, @jucie-pie

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 →