AI Infra Guard MCP Server

by Tencent• 7.3k•• Scanned•Claim this listing•Request removal
Security & Testingagentagent securityagentic aiai infraai red teaming

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

AI Infra Guard is an open-source mcp server by Tencent, written mainly in Python, with 7,256 GitHub stars and the Apache-2.0 license. Its code was last updated Oct 30, 2026.

Scan summary: scanned Nov 5, 2026 at commit 76146bf. Seen able to run shell commands, run dynamic code, read environment and secrets. Scan policy

Scanned
Full scan at 76146bf · Nov 5, 2026
Scanned
Static code scanwarn
Secrets scanfail
Dependency audit153 known vulnerabilitiesfail
Manifestnonewarn
Buildn/a
Boot & handshaken/a
Network egressn/a
Reproducible (×3)n/a

Findings (49)

  • high
    dropper issue
    Details are available to the maintainer after claiming this listing.
  • high
    credential-access issue
    Details are available to the maintainer after claiming this listing.
  • high
    code-execution issue
    Details are available to the maintainer after claiming this listing.
  • high
    secrets issue
    Details are available to the maintainer after claiming this listing.
  • high
    secrets issue
    Details are available to the maintainer after claiming this listing.
  • high
    secrets issue
    Details are available to the maintainer after claiming this listing.
  • high
    secrets issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    Research/roguehandoff20/roguehandoff/provider_proxy.py:40
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    mcp-scan/mcp_scan/tools/execute/execute_actions.py:45
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    mcp-scan/testcase/case1/main1.py:173
  • medium
    httpcore2@2.9.1: 2 known vulnerabilities
    PYSEC-2026-3844, PYSEC-2026-3844
    AIG-PromptSecurity/requirements.txt
  • medium
    httpx2@2.9.1: 10 known vulnerabilities
    PYSEC-2026-3845, PYSEC-2026-3846, PYSEC-2026-3847, PYSEC-2026-3848, PYSEC-2026-3849 +5 more
    AIG-PromptSecurity/requirements.txt
  • medium
    wheel@0.9.7: 1 known vulnerability
    PYSEC-2022-43017
    AIG-PromptSecurity/requirements.txt
  • medium
    tqdm@4.9.0: 4 known vulnerabilities
    PYSEC-2017-74, PYSEC-2026-1976, PYSEC-2017-74, PYSEC-2026-1976
    agent-scan/requirements.txt
  • medium
    github.com/klauspost/compress@1.17.6: 1 known vulnerability
    GO-2026-5841
    go.mod
  • medium
    github.com/mholt/archiver/v3@3.5.1: 2 known vulnerabilities
    GO-2024-2698, GO-2025-3605
    go.mod
  • medium
    mcp@2.0.0: 4 known vulnerabilities
    GHSA-5h93-6whr-6q8j, GHSA-84m7-p3x7-pcfv, GHSA-rwrf-2pqf-9j8j, GHSA-w4fh-qvv9-3v23
    mcp-scan/requirements.txt
  • medium
    python-multipart@0.0.9: 8 known vulnerabilities
    PYSEC-2026-1851, PYSEC-2026-1852, PYSEC-2026-3036, PYSEC-2026-3037, PYSEC-2026-3038 +3 more
    mcp-scan/requirements.txt
  • low
    In tests/examples/docs: Downloads a script and pipes it straight into a shell (often an installer command shown to users; check where it runs).
    Research/pikit/demos/live_matrix/test_agents_live.py:83
  • low
    In tests/examples/docs: Downloads a script and pipes it straight into a shell (often an installer command shown to users; check where it runs).
    mcp-scan/pytests/test_surrogate_sanitization.py:86
  • low
    In tests/examples/docs: Downloads a script and pipes it straight into a shell (often an installer command shown to users; check where it runs).
    skill-scan/pytests/test_audit_evidence.py:40
  • low
    In tests/examples/docs: Touches a sensitive credential location (SSH keys, cloud credentials, browser data or wallets). Expected for some tools, such as browser automation; check why.
    skill-scan/pytests/test_audit_evidence.py:44
  • low
    In tests/examples/docs: Downloads a script and pipes it straight into a shell (often an installer command shown to users; check where it runs).
    skill-scan/pytests/test_audit_evidence.py:60
  • low
    In tests/examples/docs: Downloads a script and pipes it straight into a shell (often an installer command shown to users; check where it runs).
    skill-scan/pytests/test_charset_smuggling.py:120
  • low
    In tests/examples/docs: Downloads a script and pipes it straight into a shell (often an installer command shown to users; check where it runs).
    skill-scan/pytests/test_hidden_content.py:92
  • low
    In tests/examples/docs: Downloads a script and pipes it straight into a shell (often an installer command shown to users; check where it runs).
    skill-scan/pytests/test_hidden_content.py:121
  • low
    Possible example credential in docs/tests: generic-api-key
    3 matches in this file
    README.md:483
  • low
    Possible example credential in docs/tests: private-key
    agent-scan/agent_scan/prompt/skills/hardcoded-secret-detection/SKILL.md:38
  • low
    Possible example credential in docs/tests: generic-api-key
    2 matches in this file
    agent-scan/agent_scan/prompt/skills/memory-rag-poisoning-detection/SKILL.md:129
  • low
    Possible example credential in docs/tests: generic-api-key
    3 matches in this file
    readme/README_ZH.md:482
  • low
    idna@3.9.0: 3 known vulnerabilities
    PYSEC-2026-215, PYSEC-2026-215, PYSEC-2026-215
    Research/SkillJack/requirements.txt
  • low
    python-dotenv@1.0.0: 3 known vulnerabilities
    PYSEC-2026-2270, PYSEC-2026-2270, PYSEC-2026-2270
    agent-scan/requirements.txt
  • low
    filippo.io/edwards25519@1.1.0: 1 known vulnerability
    GO-2026-4503
    go.mod
  • low
    github.com/cloudflare/circl@1.3.7: 2 known vulnerabilities
    GO-2025-3754, GO-2026-4550
    go.mod
  • low
    github.com/nwaples/rardecode@1.1.3: 1 known vulnerability
    GO-2025-4020
    go.mod
  • low
    github.com/refraction-networking/utls@1.6.7: 3 known vulnerabilities
    GO-2025-3638, GO-2026-4509, GO-2026-4512
    go.mod
  • low
    github.com/ulikunitz/xz@0.5.11: 1 known vulnerability
    GO-2025-3922
    go.mod
  • low
    github.com/valyala/fasthttp@1.52.0: 1 known vulnerability
    GO-2026-4950
    go.mod
  • low
    golang.org/x/mod@0.24.0: 2 known vulnerabilities
    GO-2026-6179, GO-2026-6180
    go.mod
  • low
    golang.org/x/net@0.40.0: 17 known vulnerabilities
    GO-2026-4440, GO-2026-4441, GO-2026-4918, GO-2026-5025, GO-2026-5026 +12 more
    go.mod
  • low
    golang.org/x/sys@0.33.0: 1 known vulnerability
    GO-2026-5024
    go.mod
  • low
    golang.org/x/text@0.25.0: 2 known vulnerabilities
    GO-2026-5970, GO-2026-6629
    go.mod
  • low
    No manifest declaring network access and environment variables (agent.json)

Automated result for the commit shown. See our scan policy. View the scan log

Maintainers can claim the listing to rescan, or dispute a result.

AI Infra Guard alternatives

View more →

Similar mcp servers in Security & Testing, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
AI Infra Guard (this page)
Tencent
7.3kApache-2.0Oct 30, 2026Scanned, no flagged issues
Hexstrike AI
0x4m4
13kMITAug 3, 2026Scanned, no flagged issues
Viper
FunnyWolf
5.3kNone foundMay 31, 2026Not scanned yet
Open Ontologies
fabio-rovai
2.7kMITOct 30, 2026Scanned, no flagged issues
Qu1cksc0pe
CYB3RMX
2.1kGPL-3.0Sep 18, 2026Scanned, no flagged issues
Cve MCP Server
mukul975
1.7kApache-2.0Oct 1, 2026Scanned, no flagged issues