Loading the registry…
Cloud Run MCP deployment tool
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.
3 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/GoogleCloudPlatform/cloud-run-mcp, 144 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @google-cloud/cloud-run-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 · 3.2s
v2.0.11
32 findings · 56.7s
v0.3.26
10 findings · 20.2s
v0.1.0
0 findings · 49.5s
v0.1.0
1 finding · 49.5s
v0.1.0
0 findings · 22.6s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
7 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 2, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 21, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: complete | rejected |
| Jul 20, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: complete | rejected |
| Jul 20, 2026 | Scan Halted | Clean → Flagged | agentshield: completecisco-skill-scanner: completeagent-audit-kit: complete | rejected |
| Jul 20, 2026 | Clean100 | — | agentshield ·n/a: not applicablecisco-skill-scanner ·n/a: not applicableagent-audit-kit: completetrivy: completeosv-scanner ·n/a: not applicable | completed |
| Jul 20, 2026 | Clean100 | — | agentshield ·n/a: not applicablecisco-skill-scanner ·n/a: not applicableagent-audit-kit: completetrivy: completeosv-scanner ·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 43 findings across every scanner that examined this package. None of the 3 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.
10 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, OVERSIZED_FILE · Files: /repo/.github/images/deploy_from_apps.gif, /repo/.github/images/deploycli.gif · reported by cisco-skill-scanner
7 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-OAUTH-001, AAK-OAUTH-005, FILE_MAGIC_MISMATCH · Files: test/local/mcp-server-streamable-http.test.js, test/local/clients.test.js, test/local/middleware/oauth.test.js and 4 more · reported by agent-audit-kit, 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.
3 FILE_MAGIC_MISMATCH
Files: /repo/constants.js, /repo/lib/deployment/constants.js, /repo/mcp-server.js · reported by cisco-skill-scanner
3 HIDDEN_DATA_FILE
Files: /repo/.prettierrc.json, /repo/.env.gcloud-sdk-oauth, /repo/.c8rc.json · reported by cisco-skill-scanner
3 MANIFEST_MISSING_LICENSE
Files: /repo/skills/cloud-run/SKILL.md, /repo/SKILL.md, /repo/gemini-extension/SKILL.md · reported by cisco-skill-scanner
2 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/lib/deployment/compose.js, /repo/lib/deployment/universal-maker.js · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/lib/deployment/universal-maker.js, /repo/lib/util/artifacts.js · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_NETWORK
Critical command injection and high-risk OAuth findings.
The artifact contains critical command injection vulnerabilities in `mcp-server.js`, `/repo/lib/deployment/compose.js`, and `/repo/lib/deployment/universal-maker.js`, enabling shell execution. Additionally, a high-severity finding in `mcp-server.js` indicates potential for credential access via OAuth. Multiple medium-severity findings also point to potential for file writes and further OAuth-related risks. These findings warrant attention due to the capabilities they expose.
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/lib/cloud-api/metadata.js · reported by cisco-skill-scanner
2 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/gemini-extension/SKILL.md · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: example-sources-to-deploy/nodejs/package.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: mcp-server.js · reported by agent-audit-kit
1 AAK-MCP-STDIO-CMD-INJ-002
Files: mcp-server.js · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: mcp-server.js · reported by agent-audit-kit
1 AAK-OAUTH-005
Files: lib/clients.js · 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 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/README.md · reported by nerlo-install-instruction