Loading the registry…
MCP server for Nano Banana image generation (OpenRouter by default, configurable provider)
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.
4 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.
github_release: https://github.com/aeven-ai/mcp-nanobanana, 0 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @aeven/nanobanana-mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
8 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
17 findings · 8.0s
v0.3.74
5 findings · 1.6s
v0.1.0
0 findings · 3.5s
v0.1.0
0 findings · 3.5s
v0.1.0
0 findings · 14.3s
v0.71.0
11 findings · 0.3s
v2.3.8
33 findings · 10.1s
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
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 3, 2026 | Flagged41 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
| Aug 12, 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 66 findings across every scanner that examined this package. None of the 4 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.
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/SKILL.md · reported by cisco-skill-scanner
2 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: DATA_EXFIL_JS_FS_ACCESS · Files: /repo/mcp-server/tests/unit/fileHandler.test.js · reported by 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.
4 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/mcp-server/dist/imageGenerator.js, /repo/mcp-server/src/imageGenerator.ts, /repo/scripts/verify-npm-distribution.mjs · reported by cisco-skill-scanner
4 FILE_MAGIC_MISMATCH
Files: /repo/eslint.config.js, /repo/mcp-server/dist/imageGenerator.js, /repo/mcp-server/dist/types.js and 1 more · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_NETWORK
Files: /repo/mcp-server/dist/imageGenerator.js, /repo/mcp-server/src/imageGenerator.ts · reported by cisco-skill-scanner
2 GHSA-23c5-xmqv-rm74
Files: /repo/package-lock.json · reported by osv-scanner
2 GHSA-3jxr-9vmj-r5cp
Files: /repo/package-lock.json · reported by osv-scanner
2 GHSA-3ppc-4f35-3m26
Files: /repo/package-lock.json · reported by osv-scanner
2 GHSA-7r86-cg39-jmmj
Files: /repo/package-lock.json · reported by osv-scanner
2 GHSA-f886-m6hf-6m8v
Files: /repo/package-lock.json · reported by osv-scanner
2 GHSA-mh99-v99m-4gvg
Files: /repo/package-lock.json · reported by osv-scanner
2 GHSA-rgw5-rvv9-x895
Files: /repo/package-lock.json · reported by osv-scanner
1 AAK-ANTHROPIC-SDK-001
Files: mcp-server/src/server.ts · reported by agent-audit-kit
1 AAK-DNS-REBIND-002
Files: package.json · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: mcp-server/package.json · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 CVE-2025-13466
Files: package-lock.json · reported by trivy
1 CVE-2025-15284
Files: package-lock.json · reported by trivy
1 CVE-2025-66414
Files: package-lock.json · reported by trivy
1 CVE-2025-69873
Files: package-lock.json · reported by trivy
1 CVE-2026-0621
Files: package-lock.json · reported by trivy
1 CVE-2026-12590
Files: package-lock.json · reported by trivy
1 CVE-2026-2391
Files: package-lock.json · reported by trivy
1 CVE-2026-25536
Files: package-lock.json · reported by trivy
1 CVE-2026-4923
Files: package-lock.json · reported by trivy
1 CVE-2026-4926
Files: package-lock.json · reported by trivy
1 CVE-2026-8723
Files: package-lock.json · reported by trivy
1 GHSA-25h7-pfq9-p65f
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-27v5-c462-wpq7
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-2g4f-4pwh-qvx6
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-345p-7cg4-v4c7
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-3v7f-55p6-f55p
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-52cp-r559-cp3m
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-5p4m-2wfm-xmqj
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-6rw7-vpxm-498p
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-8r9q-7v3j-jr4g
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-c2c7-rcm5-vvqj
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-h67p-54hq-rp68
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-j3q9-mxjg-w52f
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-mh29-5h37-fv8m
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-q8mj-m7cp-5q26
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-rf6f-7fwh-wjgh
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-v422-hmwv-36x6
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-w48q-cv73-mx4w
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-w7fw-mjwx-w883
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-wqch-xfxh-vrr4
Files: /repo/package-lock.json · reported by osv-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md · reported by cisco-skill-scanner
1 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md · reported by cisco-skill-scanner
Artifact contains critical command injection vulnerabilities and high-severity dependencies.
The artifact includes critical command injection vulnerabilities in `imageGenerator.js`, `imageGenerator.ts`, and `verify-npm-distribution.mjs`, which could lead to shell execution. It also uses an Anthropic SDK in `mcp-server/src/server.ts`, indicating network egress for AI services, and has a DNS rebinding vulnerability in `package.json`. Additionally, numerous high-severity vulnerabilities are present in transitive dependencies listed in `package-lock.json`.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Showing 25 of 31; the rest are in the per-scanner reports above.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.