aig-agent-redteam

aig-agent-redteam is an Agent security & guardrails skill for AI agents, published by Tencent in the AI-Infra-Guard repository on GitHub. Skillspace rates aig-agent-redteam C (73/100) and it passed the safety scan; the rating is based on static analysis only.

当用户要求 AI/Agent 安全评估、蓝军演习、AI 安全审查、提示词注入测试、MCP/Skill/插件/代码包审计、Agent 工具链滥用测试，或需要生成类似渗透测试报告的 Markdown/HTML 时，必须使用本 skill。本 skill 让 Agent 以授权蓝军视角成为 AI 安全专家，面向 AI 产品、Agent、MCP Server、Skill、代码仓库和 AI 基础设施进行安全演习。优先使用第一性原理推理和真实证据，而不是机械跑 payload 库；脚本只用于 HTTP 指纹识别、证据聚合、报告渲染等确定性辅助任务。

Grade
C
Quality
73 / 100
Safety
Passed
GitHub stars
4,125

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubTencent/AI-Infra-Guard

Our review

Architecture
81 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
Apache-2.0
Adoption
Adopted by 0 other repositories, in 0 collections
Scope
Portable: works in any project. general AI/agent red-team methodology for any target

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More Agent security & guardrails skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.