Loading the registry…
Byul MCP server (stdio) proxying Byul REST API
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
172 critical findings reported by cisco-skill-scanner, 170 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/byul-ai/mcp-server, 3069 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @byul/mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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 · 0.6s
v2.0.11
3060 findings · 97.6s
v0.3.74
7 findings · 7.2s
v0.1.0
1 finding · 4.6s
v0.1.0
0 findings · 4.6s
v0.1.0
0 findings · 9.4s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 19, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | rejected |
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 3,068 findings across every scanner that examined this package. 2 of 172 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 2,875 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
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.
16 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: SECRET_JWT_TOKEN, HIDDEN_EXECUTABLE_SCRIPT · Files: /repo/node_modules/.pnpm/zod@3.25.76/node_modules/zod/src/v4/mini/tests/string.test.ts, /repo/node_modules/.pnpm/zod@3.25.76/node_modules/zod/src/v3/tests/date.test.ts, /repo/node_modules/.pnpm/get-proto@1.0.1/node_modules/get-proto/test/index.js and 10 more · reported by cisco-skill-scanner
4 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: COMMAND_INJECTION_EVAL, HIDDEN_EXECUTABLE_SCRIPT · Files: /repo/node_modules/.pnpm/@modelcontextprotocol+sdk@1.17.3/node_modules/@modelcontextprotocol/sdk/dist/esm/examples/client/simpleOAuthClient.js, /repo/node_modules/.pnpm/@modelcontextprotocol+sdk@1.17.3/node_modules/@modelcontextprotocol/sdk/dist/cjs/examples/client/simpleStreamableHttp.d.ts, /repo/node_modules/.pnpm/@modelcontextprotocol+sdk@1.17.3/node_modules/@modelcontextprotocol/sdk/dist/cjs/examples/server/toolWithSampleServer.d.ts · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
56 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/node_modules/.pnpm/@types+node@22.17.2/node_modules/@types/node/child_process.d.ts, /repo/node_modules/.pnpm/cross-spawn@7.0.6/node_modules/cross-spawn/index.js, /repo/node_modules/.pnpm/tsx@4.20.4/node_modules/tsx/dist/cli.cjs and 5 more · reported by cisco-skill-scanner
54 COMMAND_INJECTION_EVAL
Files: /repo/node_modules/.pnpm/ajv@6.12.6/node_modules/ajv/dist/ajv.bundle.js, /repo/node_modules/.pnpm/ajv@6.12.6/node_modules/ajv/lib/ajv.d.ts, /repo/node_modules/.pnpm/ajv@6.12.6/node_modules/ajv/lib/ajv.js and 13 more · reported by cisco-skill-scanner
47 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/node_modules/.pnpm/math-intrinsics@1.1.0/node_modules/math-intrinsics/max.js, /repo/node_modules/.pnpm/zod@3.25.76/node_modules/zod/v3/external.d.ts, /repo/node_modules/.pnpm/ajv@6.12.6/node_modules/ajv/lib/dotjs/format.js and 44 more · reported by cisco-skill-scanner
16 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/node_modules/.pnpm/ajv@6.12.6/node_modules/ajv/dist/ajv.bundle.js, /repo/node_modules/.pnpm/ajv@6.12.6/node_modules/ajv/dist/ajv.min.js, /repo/node_modules/.pnpm/ajv@6.12.6/node_modules/ajv/lib/compile/index.js and 4 more · reported by cisco-skill-scanner
2,754 The review budget for this scan was already spent before these findings were reached.
Rules: HIDDEN_EXECUTABLE_SCRIPT, AAK-DNS-REBIND-002, AAK-ANTHROPIC-SDK-001 and 21 more · Files: /repo/node_modules/.pnpm/zod@3.25.76/node_modules/zod/v4/locales/zh-TW.js, /repo/node_modules/.pnpm/uri-js@4.4.1/node_modules/uri-js/dist/es5/uri.all.d.ts, /repo/node_modules/.pnpm/@modelcontextprotocol+sdk@1.17.3/node_modules/@modelcontextprotocol/sdk/dist/cjs/server/sse.js and 2372 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-behavioral
75 The review call did not complete.
Rules: HIDDEN_EXECUTABLE_SCRIPT · Files: /repo/node_modules/.pnpm/zod@3.25.76/node_modules/zod/src/v3/tests/validations.test.ts, /repo/node_modules/.pnpm/zod@3.25.76/node_modules/zod/src/v4/classic/tests/lazy.test.ts, /repo/node_modules/.pnpm/@modelcontextprotocol+sdk@1.17.3/node_modules/@modelcontextprotocol/sdk/dist/cjs/shared/auth-utils.js and 72 more · reported by cisco-skill-scanner
46 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: COMMAND_INJECTION_EVAL, COMMAND_INJECTION_JS_CHILD_PROCESS, YARA_coercive_injection_generic and 1 more · Files: /repo/node_modules/.pnpm/@types+node@22.17.2/node_modules/@types/node/repl.d.ts, /repo/node_modules/.pnpm/@types+node@22.17.2/node_modules/@types/node/vm.d.ts, /repo/node_modules/.pnpm/typescript@5.9.2/node_modules/typescript/lib/lib.es5.d.ts and 6 more · reported by cisco-skill-scanner
Critical command injection and secret exfiltration risks.
This artifact exhibits critical command injection vulnerabilities through the use of `eval`, `Function` constructor, and `child_process` for shell execution, which could lead to arbitrary code execution. A high-severity finding also indicates potential secret exfiltration to the network. Additionally, numerous hidden executable scripts are present, and password variables are identified.
Concern level assessed by the review: Critical. 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.
Showing 25 of 25; the rest are in the per-scanner reports above.