Loading the registry…
A capability-first MCP workbench for executable mathematics
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.
105 critical findings reported by cisco-skill-scanner, agent-audit-kit, 18 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/morluto/jacobian, 881 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- jacobian
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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.
v2.0.11
425 findings · 135.9s
v0.3.26
421 findings · 86.1s
v0.1.0
1 finding · 50.6s
v0.1.0
1 finding · 50.6s
v0.1.0
0 findings · 42.7s
v1.4.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.2s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 3, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Aug 2, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-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 848 findings across every scanner that examined this package. 85 of 105 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 1 finding 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.
308 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: COMMAND_INJECTION_JS_CHILD_PROCESS, AAK-MCP-STDIO-CMD-INJ-001, AAK-DNS-REBIND-001 and 6 more · Files: /repo/npm/cli-e2e.test.mjs, /repo/npm/npm-packaging.test.mjs, tests/boundary/mcp/test_mcp_operations.py and 291 more · reported by cisco-skill-scanner, agent-audit-kit
71 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-001, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner
35 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: COMPOUND_EXTRACT_EXECUTE, AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION and 1 more · Files: /repo/docs/contributing/cddlib-hv-provider-spike.md, /repo/docs/contributing/SKILL.md, AGENTS.md and 21 more · reported by cisco-skill-scanner, agent-audit-kit
3 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: opt.nerlo-rules.nerlo-py-secret-to-network-egress, MANIFEST_INVALID_NAME · Files: /repo/.github/scripts/manage-test-timings, /repo/.github/ISSUE_TEMPLATE/SKILL.md, /repo/.github/SKILL.md · reported by nerlo-behavioral, cisco-skill-scanner
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.
147 MANIFEST_MISSING_LICENSE
Files: /repo/.agents/skills/verifier-evaluations/SKILL.md, /repo/.agents/skills/harbor-benchmarks/SKILL.md, /repo/SKILL.md and 144 more · reported by cisco-skill-scanner
145 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/research/SKILL.md, /repo/npm/SKILL.md and 142 more · reported by cisco-skill-scanner
56 FILE_MAGIC_MISMATCH
Files: /repo/benchmarks/datasets/agent-workflow-v1/cubic-image-classification/solution/answer.txt, /repo/benchmarks/datasets/agent-workflow-v1/ratio-test-boundary-separation/solution/answer.txt, /repo/benchmarks/datasets/agent-workflow-v1/research-status-evidence-audit/solution/answer.txt and 14 more · reported by cisco-skill-scanner
19 AAK-TASKS-003
Files: tools/check_benchmark_adapters.py, src/jacobian/adapters/mcp/guidance.py, benchmarks/tooling/harbor_suite.py and 16 more · reported by agent-audit-kit
14 AAK-HEALTHCARE-AI-004
Files: CHANGELOG.md, benchmarks/README.md, .agents/skills/harbor-benchmarks/SKILL.md and 11 more
1 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: SECRET_PASSWORD_VAR · Files: /repo/tests/unit/tooling/test_harbor_validation.py · reported by cisco-skill-scanner
Artifact has critical command injection and PII handling risks.
The artifact contains multiple critical command injection vulnerabilities, specifically through `eval` in Python files within `src/jacobian/` and via child processes in `npm/bin/launcher.cjs`, which could lead to shell execution. It also handles or contains Indian PII in `benchmarks/datasets/` and has a potential DNS rebinding vulnerability in `deploy/smoke_remote.py` that could facilitate network egress. Additionally, generic coercive injection patterns are present in skill definitions.
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.
13 COMMAND_INJECTION_EVAL
Files: /repo/src/jacobian/domains/graph_optimization/exact_search.py, /repo/src/jacobian/domains/graph_optimization/invariants.py, /repo/src/jacobian/domains/graph_optimization/operations.py and 6 more · reported by cisco-skill-scanner
11 HIDDEN_DATA_FILE
Files: /repo/.agents/skills/harbor-benchmarks/SKILL.md, /repo/.markdown-link-check.json, /repo/.jscpd.json and 8 more · reported by cisco-skill-scanner
6 EXCESSIVE_FILE_COUNT
Files: /repo/benchmarks/., /repo/benchmarks/datasets/research-diagnostics-v1/., /repo/benchmarks/datasets/public-reproductions-v1/. and 3 more · reported by cisco-skill-scanner
3 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/src/jacobian/domains/_certified_snf.py, /repo/src/jacobian/experiments/service.py, /repo/src/jacobian/search/service.py · reported by cisco-skill-scanner
2 AAK-INDIA-PII-001
Files: benchmarks/datasets/agent-workflow-v1/exact-farkas-ldl-slice/solution/submission.json, benchmarks/datasets/agent-workflow-v1/exact-farkas-ldl-slice/solution/farkas-slice-certificate.json · reported by agent-audit-kit
2 AAK-OAUTH-001
Files: src/jacobian/checker_installation.py, src/jacobian/registry.py · reported by agent-audit-kit
2 AAK-SECRET-004
Files: deploy/smoke_remote.py · reported by agent-audit-kit
2 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/npm/bin/launcher.cjs · reported by cisco-skill-scanner
2 YARA_coercive_injection_generic
Files: /repo/.agents/skills/verifier-evaluations/references/SKILL.md · reported by cisco-skill-scanner
1 AAK-DNS-REBIND-001
Files: deploy/smoke_remote.py · reported by agent-audit-kit
1 AAK-IPI-WILD-CORPUS-001
Files: src/jacobian/persistence/migrations.py · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 LOW_ANALYZABILITY
Files: /repo/npm · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/README.md · reported by nerlo-install-instruction
1 YARA_system_manipulation_generic
Files: /repo/deploy/install.sh · reported by cisco-skill-scanner
Showing 25 of 29; the rest are in the per-scanner reports above.