Nagomi forensic server for Gemini CLI - PhD-level medical research analysis with AI-powered evidence synthesis and ABC-TOM intelligent reference verification
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.
24 critical findings reported by cisco-skill-scanner, agent-audit-kit. 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/avivlyweb/pubmed-gemini-extension, 141 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- pubmed-gemini-extension
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 · 0.9s
v2.0.11
101 findings · 9.1s
v0.3.74
24 findings · 8.4s
v0.1.0
7 findings · 4.9s
v0.1.0
9 findings · 4.9s
v0.1.0
0 findings · 11.7s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: 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 |
|---|---|---|---|---|
| Sep 3, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | rejected |
| Aug 11, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | 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 141 findings across every scanner that examined this package. None of the 24 findings rated critical by their scanner were dismissed.
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.
8 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_prompt_injection_unicode_steganography, HIDDEN_DATA_FILE, BINARY_FILE_DETECTED · Files: /repo/docs/media/nagomi-demo.gif, /repo/docs/media/nagomi-demo.mp4, /repo/docs/images/.!32888!Screenshot 2026-01-25 at 13.41.13.png · reported by cisco-skill-scanner
3 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: AAK-MCP-018 · Files: pubmed-gemini/example.test.ts, VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/example.test.js, VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/example.test.ts · reported by agent-audit-kit
2 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: PIPELINE_TAINT_FLOW, AAK-GHA-IMMUTABLE-001 · Files: /repo/.github/workflows/release.yml, .github/workflows/release.yml · reported by cisco-skill-scanner, agent-audit-kit
1 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-HEALTHCARE-AI-004 · Files: CLAUDE.md · 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.
19 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/pubmed-gemini/pubmed-wrapper.js, /repo/VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/pubmed-wrapper.js · reported by cisco-skill-scanner
16 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/pubmed-synthesis/SKILL.md, /repo/.claude/skills/pubmed-search/SKILL.md, /repo/.claude/skills/pubmed-export/SKILL.md and 13 more · reported by cisco-skill-scanner
14 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/install.sh · reported by cisco-skill-scanner
11 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/pubmed-gemini/SKILL.md, /repo/ABC-TOM/T-tools/SKILL.md and 8 more · reported by cisco-skill-scanner
10 AAK-HEALTHCARE-AI-004
Files: GEMINI.md, CONTRIBUTING.md, pubmed-gemini/GEMINI.md and 7 more · reported by agent-audit-kit
Artifact contains critical command injection and remote code execution vulnerabilities.
The artifact exhibits critical command injection vulnerabilities in `pubmed-wrapper.js` and `report_generator.py`, allowing for shell execution and SQL injection. It also includes a critical finding for fetching and executing remote code via `install.sh`. Additionally, the artifact fetches sensitive configuration data in `example.js`, which could lead to credential access.
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.
Files: /repo/VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/commands/nagomi/verify.toml, /repo/VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/commands/nagomi/analyze.toml, /repo/pubmed-gemini/commands/nagomi/search.toml and 1 more · reported by cisco-skill-scanner
7 MANIFEST_INVALID_NAME
Files: /repo/ABC-TOM/C-core/SKILL.md, /repo/gemini/ABC-TOM/C-core/SKILL.md, /repo/ABC-TOM/M-memory/SKILL.md and 4 more · reported by cisco-skill-scanner
5 HIDDEN_DATA_FILE
Files: /repo/pubmed-gemini/.genkit/traces_idx/genkit.metadata, /repo/VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/.genkit/traces_idx/genkit.metadata · reported by cisco-skill-scanner
5 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/pubmed-gemini/pubmed-wrapper.js · reported by nerlo-behavioral
3 LOW_ANALYZABILITY
Files: /repo/pubmed-gemini, /repo/VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini, /repo/VKB/pubmedmcp/pubmed-mcp/pubmedgemini · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/install.ps1, /repo/install.sh · reported by nerlo-install-instruction
3 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/install.sh · reported by nerlo-install-instruction
2 AAK-MCP-018
Files: pubmed-gemini/example.js, VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/example.js · reported by agent-audit-kit
2 AAK-MCP-MARKETPLACE-CONFIG-FETCH-001
Files: pubmed-gemini/example.js, VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/example.js · reported by agent-audit-kit
2 AAK-MCP-SSRF-001
Files: pubmed-mcp/pubmed_mcp.py, VKB/pubmedmcp/pubmed-mcp/pubmed_mcp.py · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/VKB/pubmedmcp/pubmed-mcp/pubmedgemini/pubmed-gemini/example.js, /repo/pubmed-gemini/example.js · reported by nerlo-behavioral
2 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/install.sh · reported by nerlo-install-instruction
2 SQL_INJECTION_STRING_FORMAT
Files: /repo/VKB/pubmedmcp/pubmed-mcp/reference_checker/report_generator.py, /repo/pubmed-mcp/reference_checker/report_generator.py · reported by cisco-skill-scanner
1 AAK-MCP-006
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: .mcp.json · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 COMPOUND_FETCH_EXECUTE
Files: /repo/install.sh · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/install.sh · reported by nerlo-install-instruction
1 PIPELINE_TAINT_FLOW
Files: /repo/install.sh · reported by cisco-skill-scanner
1 PYCACHE_FILES_DETECTED
Files: /repo/VKB/pubmedmcp/pubmed-mcp/reference_checker/__pycache__ · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md · reported by cisco-skill-scanner
Showing 25 of 36; the rest are in the per-scanner reports above.