A MCP server for OpenWrt devices. This is a very early version and may contain unexpected errors.
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.
5 critical findings reported by trivy, osv-scanner. The composite score alone does not reflect this — read the per-scanner reports below.
pypi: openwrt-mcp @ 0.1.7, 0 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- openwrt-mcp
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.
v2.0.11
9 findings · 6.5s
v0.3.74
4 findings · 0.8s
v0.1.0
6 findings · 3.0s
v0.1.0
0 findings · 3.0s
v0.1.0
0 findings · 8.1s
v0.71.0
49 findings · 0.2s
v2.3.8
50 findings · 1.3s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
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
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 20, 2026 | Flagged35 | — | agentshield ·n/a: not applicablecisco-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 |
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 118 findings across every scanner that examined this package. None of the 5 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 83 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
The model could have called any of these a false positive and did not.
6 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/openwrt_mcp/openwrt.py · reported by cisco-skill-scanner
2 GHSA-rcfx-77hg-w2wv
Files: uv.lock, /repo/uv.lock · reported by trivy, osv-scanner
1 AAK-SSRF-002
Files: openwrt_mcp/openwrt.py · reported by agent-audit-kit
1 CVE-2025-59420
Files: uv.lock · reported by trivy
1 CVE-2025-62800
Files: uv.lock · reported by trivy
1 CVE-2025-64340
Files: uv.lock · reported by trivy
1 CVE-2025-66471
Files: uv.lock · reported by trivy
1 CVE-2026-25645
Files: uv.lock · reported by trivy
1 CVE-2026-26007
Files: uv.lock · reported by trivy
1 CVE-2026-28684
Files: uv.lock · reported by trivy
1 CVE-2026-40347
Files: uv.lock · reported by trivy
1 CVE-2026-45409
Files: uv.lock · reported by trivy
1 CVE-2026-53537
Files: uv.lock · reported by trivy
1 CVE-2026-53538
Files: uv.lock · reported by trivy
1 CVE-2026-53540
Files: uv.lock · reported by trivy
1 GHSA-537c-gmf6-5ccf
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-1202
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-1364
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-1365
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-141
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-161
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-1617
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-2119
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-215
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-2270
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-2280
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-2475
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-2476
Files: /repo/uv.lock · reported by osv-scanner
1 PYSEC-2026-3041
Files: /repo/uv.lock · reported by osv-scanner
80 The model's answer could not be read.
Rules: PYSEC-2026-36, PYSEC-2026-338, CVE-2026-27962 and 71 more · Files: /repo/uv.lock, uv.lock, /repo/openwrt_mcp/openwrt.py and 2 more · reported by osv-scanner, trivy, nerlo-behavioral and 1 more
2 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: TOOL_ABUSE_UNDECLARED_NETWORK, MANIFEST_MISSING_LICENSE · Files: /repo/repo/README.md, /repo/SKILL.md · reported by cisco-skill-scanner
1 The model did not answer for these findings.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION · Files: /repo/SKILL.md · reported by cisco-skill-scanner
Critical vulnerabilities and network egress risks identified.
The artifact contains critical vulnerabilities in its dependencies, as indicated by multiple PYSEC and CVE findings in `uv.lock`. Additionally, the `openwrt_mcp/openwrt.py` component exhibits high-severity issues, including an unauthenticated server, Server-Side Request Forgery (SSRF), and multiple instances of sensitive data being sent over the network. These findings suggest potential for unauthorized access, network egress, and credential exposure.
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 64; the rest are in the per-scanner reports above.