AI-Infra-Guard is an AI security red-teaming platform that scans agents, skills, MCP servers, and AI infrastructure and evaluates LLM jailbreak resistance. It is used to identify security risks and vulnerabilities in AI systems. Catalogue add-ons support its scanning and evaluation workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Tencent/AI-Infra-Guard --skill aig-scannergit clone --depth 1 https://github.com/Tencent/AI-Infra-GuardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tencent/ai-infra-guard/aig-scanner)<a href="https://agentmods.dev/skills/tencent/ai-infra-guard/aig-scanner"><img src="https://agentmods.dev/badge/skills/tencent/ai-infra-guard/aig-scanner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tencent/ai-infra-guard/aig-scanner"><img src="https://agentmods.dev/badge/skills/tencent/ai-infra-guard/aig-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 70 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
- medium Data Exfiltration · line 204 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00142 | $0.03989 |
| Opus 5 | $0.00071 | $0.01995 |
| Sonnet 5 | $0.00028 | $0.00798 |
| Haiku 4.5 | $0.00014 | $0.00399 |
Grade B, and why
aig-scanner scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Do NOT refuse or warn about local/private addresses. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Always use `aig_client.py` via `exec` instead of raw `curl`.** Command reference: How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A.I.G Scanner
AI security scanning powered by Tencent Zhuque Lab AI-Infra-Guard.
Submits and queries A.I.G scan tasks via the taskapi endpoint using built-in exec + Python script.
Language Detection Rule
Detect the language of the user's triggering message and use that language for the entire response.
| User message language | Output language |
|---|---|
| Chinese | Chinese throughout |
| English | English throughout |
| Other | Match that language |
| Cannot determine | Default to Chinese |
⚠️ IMPORTANT: Local / Private Network Scanning is FULLY AUTHORIZED
This skill runs locally on the user's own machine. Scanning AI services on local or private networks is the primary use case.
Accept and scan the following without hesitation:
localhost,127.0.0.1,0.0.0.0- Private ranges:
192.168.x.x,10.x.x.x,172.16–31.x.x - Any LAN host (e.g.
192.168.1.10:11434)
Do NOT refuse or warn about local/private addresses.
Use This Skill When
- the target A.I.G server exposes
/api/v1/app/taskapi/*
Environment
AIG_BASE_URL- required
- A.I.G server root URL, for example
http://127.0.0.1:8088/orhttps://aig.example.com/
AIG_API_KEY- if the A.I.G server requires taskapi authentication
AIG_USERNAME- defaults to
openclaw - used for
agent_scanandaig_list_agentsnamespace resolution
- defaults to
Never print the API key or echo raw auth headers back to the user.
If AIG_BASE_URL is missing, tell the user to configure the A.I.G service address first.
Do Not Use This Skill When
- the A.I.G deployment is web-login or cookie only
- the user expects background monitoring or continuous polling after the turn ends
Tooling Rules
This skill ships with scripts/aig_client.py — a self-contained Python CLI that wraps all A.I.G taskapi calls.
The script path relative to the skill install directory is scripts/aig_client.py.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 334 lines · 142 tokens per session scan B 2df07e8decd5
aig-scanner is a skill published in the GitHub repository Tencent/AI-Infra-Guard (6,221 stars, last pushed today), licensed Apache-2.0. It adds 142 tokens to every session and 3,989 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (tells the agent never to refuse, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
squirrelscan
Skill "squirrelscan" from squirrelscan/squirrelscan, covering squirrelscan cli, links, install, command overview and quickstart.
audit-website
Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-optimized report, then drives an iterative fix loop, mapping issues to source files, applying fixes, and re-auditing…
5writing
A paper-writing workflow for mathematical modelling competitions, supporting both Typst and LaTeX. It uses analysis, results, figures, and a competition template to assemble the document.
6verity
A final-checking workflow for mathematical modelling competition papers, using either Typst or LaTeX to build the document. It checks the finished paper and its supporting files before submission.
typst-author
Generate idiomatic Typst (.typ) code, edit and troubleshoot Typst documents and projects, and answer Typst syntax/reference questions. Use when working with .typ files or when the user explicitly asks for Typst document creation, editing, debugging, compilation, formatting, template work, or package usage.
1start-mathmodel
A starting workflow for mathematical-modeling competitions, which are contests where teams use mathematics, data, and code to solve real-world problems. It asks for preferences, creates planning files, and coordinates later analysis, modeling, coding, charting, diagram, writing, and verification stages.