SkillSpector Agent Skill

by NVIDIA• 24k•• Scanned•Claim this listing•Request removal
Security & Testingagent securityagent skillsagentic aiai securityclaude code

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

SkillSpector is an open-source agent skill by NVIDIA, written mainly in Python, with 23,773 GitHub stars and the Apache-2.0 license. Its code was last updated Oct 31, 2026.

Scan summary: scanned Nov 5, 2026 at commit 9a08b0a. Seen able to read environment and secrets, connect to the internet. Scan policy

Scanned
Full scan at 9a08b0a · Nov 5, 2026
Scanned Builds
Static code scanwarn
Secrets scanpass
Dependency audit64 known vulnerabilitiesfail
Manifestnonewarn
Buildpass
Boot & handshaken/a
Network egressn/a
Reproducible (×3)n/a

Findings (29)

  • high
    credential-access 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
    credential-access 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
    credential-access 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
    credential-access 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
    credential-access 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
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • medium
    Turns off TLS certificate checking, allowing traffic interception.
    src/skillspector/nodes/analyzers/static_patterns_supply_chain.py:428
  • medium
    cryptography@49.0.0: 1 known vulnerability
    PYSEC-2026-3552
    uv.lock
  • medium
    dulwich@1.2.6: 5 known vulnerabilities
    GHSA-35mr-4567-66vg, GHSA-5fqc-mrg8-w798, GHSA-8mcx-5rqc-vhmf, GHSA-8w8g-wq8h-fq33, GHSA-cm62-gvxx-vmxx
    uv.lock
  • medium
    filelock@3.29.4: 9 known vulnerabilities
    GHSA-567q-5qvw-pf92, GHSA-69hj-f68j-2879, GHSA-8mx5-7m5m-r77g, GHSA-9vhv-jxww-xfm5, GHSA-cwqr-hh33-gh44 +4 more
    uv.lock
  • medium
    langgraph-api@0.10.0: 1 known vulnerability
    GHSA-4hm6-w6qq-w73v
    uv.lock
  • medium
    mcp@1.29.0: 4 known vulnerabilities
    GHSA-5h93-6whr-6q8j, GHSA-84m7-p3x7-pcfv, GHSA-rwrf-2pqf-9j8j, GHSA-w4fh-qvv9-3v23
    uv.lock
  • medium
    msgpack@1.2.1: 1 known vulnerability
    GHSA-j586-36cw-2gc2
    uv.lock
  • medium
    pyasn1@0.6.4: 4 known vulnerabilities
    GHSA-2qm8-x737-gmw5, GHSA-9m75-vc3g-4x39, GHSA-fm9c-5rcf-2q5p, GHSA-mm57-4v3p-rchx
    uv.lock
  • medium
    virtualenv@21.5.1: 19 known vulnerabilities
    PYSEC-2026-4011, PYSEC-2026-4012, PYSEC-2026-4013, PYSEC-2026-4014, GHSA-394h-qwmc-48pf +14 more
    uv.lock
  • low
    Possible example credential in docs/tests: jwt
    tests/nodes/test_report_provenance_boundary.py:23
  • low
    Possible example credential in docs/tests: generic-api-key
    2 matches in this file
    tests/opencode/skillspector_scan_lib.test.ts:103
  • low
    Possible example credential in docs/tests: jwt
    tests/unit/test_llm_provenance.py:479
  • low
    Possible example credential in docs/tests: generic-api-key
    tests/nodes/analyzers/test_static_yara.py:640
  • low
    langgraph@1.2.6: 1 known vulnerability
    GHSA-3fx2-cqw9-xr3c
    uv.lock
  • low
    langgraph-cli@0.4.30: 1 known vulnerability
    GHSA-8prr-f582-jqq3
    uv.lock
  • low
    opentelemetry-api@1.43.0: 1 known vulnerability
    GHSA-xcq7-p3pf-p88h
    uv.lock
  • low
    setuptools@82.0.1: 2 known vulnerabilities
    PYSEC-2026-3447, GHSA-xmj3-9gf7-h52w
    uv.lock
  • low
    No manifest declaring network access and environment variables (agent.json)

Network activity

During install
registry.npmjs.org
While running
Not run — the code wasn't started in this scan

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.

SkillSpector alternatives

View more →

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

NameStarsLicenceLast updatedScan
SkillSpector (this page)
NVIDIA
24kApache-2.0Oct 31, 2026Scanned, no flagged issues
Claude Red
SnailSploit
10kMITOct 12, 2026Scanned, no flagged issues
Skills
trailofbits
7.9kCC-BY-SA-4.0Oct 28, 2026Scanned, no flagged issues
Replica Skill
Jakeschincariol
6.9kMITOct 3, 2026Scanned, no flagged issues
Claude BugHunter
elementalsouls
5.4kMITNov 1, 2026Scanned, no flagged issues
VulnClaw
Netw0rkNoob
3.8kMITOct 30, 2026Scanned, no flagged issues