Loading the registry…
MCP server for local LLMs — connects to LM Studio or any OpenAI-compatible endpoint
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
github: https://github.com/houtini-ai/lm, 114 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @houtini/lm
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
7 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
0 findings · 0.5s
v2.0.11
22 findings · 7.2s
v0.3.26
6 findings · 1.0s
v0.1.0
9 findings · 29.3s
v0.1.0
0 findings · 29.3s
v0.71.0
7 findings · 0.2s
v2.3.8
7 findings · 6.6s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 8, 2026 | Flagged51 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 51 findings across every scanner that examined this package.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
3 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: docs/SETUP-VLLM.md, /repo/docs/SKILL.md · reported by agent-audit-kit, cisco-skill-scanner
1 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/release-auto.yml · reported by agent-audit-kit
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
13 DATA_EXFIL_JS_NETWORK
Files: /repo/benchmark.mjs, /repo/shakedown.mjs, /repo/src/index.ts and 3 more · reported by cisco-skill-scanner
9 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/benchmark.mjs, /repo/shakedown.mjs, /repo/test-vllm-thinking.mjs and 1 more · reported by nerlo-behavioral
2 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/add-shebang.mjs · reported by cisco-skill-scanner
2 GHSA-frvp-7c67-39w9
Files: package-lock.json, /repo/package-lock.json · reported by trivy, osv-scanner
2 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/manual/SKILL.md · reported by cisco-skill-scanner
2 SOCIAL_ENG_VAGUE_DESCRIPTION
Artifact exhibits network egress of secrets and high-severity vulnerabilities.
The artifact contains code that facilitates network egress of secrets, identified in multiple JavaScript files such as `benchmark.mjs` and `shakedown.mjs`. It also includes a high-severity finding related to credential access in `src/inference-lock.ts`. Additionally, several high-severity vulnerabilities are present in dependencies, as indicated by `package-lock.json` entries.
Concern level assessed by the review: High. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
1 AAK-ANTHROPIC-SDK-001
Files: src/index.ts · reported by agent-audit-kit
1 AAK-HEALTHCARE-AI-004
Files: README.md · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SECRET-004
Files: src/inference-lock.ts · reported by agent-audit-kit
1 CVE-2026-16221
Files: package-lock.json · reported by trivy
1 CVE-2026-18446
Files: package-lock.json · reported by trivy
1 CVE-2026-54272
Files: package-lock.json · reported by trivy
1 CVE-2026-69192
Files: package-lock.json · reported by trivy
1 CVE-2026-69198
Files: package-lock.json · reported by trivy
1 CVE-2026-69207
Files: package-lock.json · reported by trivy
1 GHSA-22jq-vg5j-6vgg
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-4xrf-jv44-h6hh
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-7p8r-x3mc-p8w7
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-8j4g-w8fx-2239
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-mwp4-54f8-5fhr
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-v2hh-gcrm-f6hx
Files: /repo/package-lock.json · reported by osv-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner