aig-scanner
A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard.
Skill by TencentOfficial
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tencent-aig-scanner
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, devops, ml, security, security-scanning, llm-evaluation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/aig-scanner
What's inside
- Skill name
aig-scanner- Description
- A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard. Uses built-in exec + Python script, no plugin required. Requires AIG_BASE_URL to be configured. Triggers on: scan AI service, AI vulnerability scan, scan AI infra, check CVE, audit AI service, scan MCP, scan skills, audit AI tools, scan agent, red-team LLM, jailbreak test, 扫描AI服务, 检查AI漏洞, 扫描AI工具, 检查MCP安全, 审计Agent, 越狱测试.
- License
- MIT
- Instructions
- 293 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- README.md
- README.zh-CN.md
- SKILL.md
- aig_client.py · scripts/
More from Tencent/AI-Infra-Guard
- 0.849score
tool-abuse-detection
TencentOfficial
Detect tool misuse and unexpected code execution via dialogue testing.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
web-exfiltration-detection
TencentOfficial
Detect data exfiltration via URL path encoding and chained web_fetch navigation.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
authorization-bypass-detection
TencentOfficial
Detect privilege escalation and unauthorized access via dialogue.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
indirect-injection-detection
TencentOfficial
Detect indirect prompt injection (goal hijack).
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
memory-rag-poisoning-detection
TencentOfficial
Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.846score
hardcoded-secret-detection
TencentOfficial
Detect hardcoded secrets in code or configuration accessible to the target agent.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.846score
agentic-supply-chain-detection
TencentOfficial
Detect agentic supply-chain risks: compromised dependencies, malicious plugins/tools/models, and untrusted update sources.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.846score
memory-poisoning-detection
TencentOfficial
Detect persistent instruction injection or long-term memory poisoning.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.846score
owasp-asi
TencentOfficial
OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.846score
data-leakage-detection
TencentOfficial
Detect sensitive information disclosure via escalating dialogue probes.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.846score
direct-injection-detection
TencentOfficial
Detect direct prompt injection or instruction override via user message (no external content).
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.846score
file-path-traversal-detection
TencentOfficial
Detect unsafe file handling and path traversal in upload/save/extract flows.
SkillAFreshness: A★ 7.1KClaude Code +9
Compare and alternatives
Featured in
Signals
- Stars
- 7,079
- Forks
- 676
- Open issues
- 10
- Last commit (this folder)
- Jun 29, 2026 (4 months ago)
- Last release
- Oct 22, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Tencent/AI-Infra-Guard
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Tencent
- 0.849score
indirect-injection-detection
TencentOfficial
Detect indirect prompt injection (goal hijack).
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
authorization-bypass-detection
TencentOfficial
Detect privilege escalation and unauthorized access via dialogue.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
web-exfiltration-detection
TencentOfficial
Detect data exfiltration via URL path encoding and chained web_fetch navigation.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
tool-abuse-detection
TencentOfficial
Detect tool misuse and unexpected code execution via dialogue testing.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
memory-rag-poisoning-detection
TencentOfficial
Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.846score
file-path-traversal-detection
TencentOfficial
Detect unsafe file handling and path traversal in upload/save/extract flows.
SkillAFreshness: A★ 7.1KClaude Code +9
Cite this page
aig-scanner skill. Agent Mart. https://agentmart.dev/skills/tencent-aig-scanner (last updated 2026-10-24)