Loading the registry…
ArkGate — architecture co-pilot for AI TypeScript (write gate, CI gate, plan/loop; optional ArkRules)
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.
387 critical findings reported by cisco-skill-scanner, agent-audit-kit, 70 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 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/pedroknigge/arkgate, 3688 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- arkgate
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
4 findings · 1.2s
v2.0.11
2289 findings · 33.2s
v0.3.26
210 findings · 12.0s
v0.1.0
1 finding · 35.5s
v0.1.0
2 findings · 35.6s
v0.1.0
0 findings · 40.6s
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: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Aug 1, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-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 2,506 findings across every scanner that examined this package. 317 of 387 findings rated critical by their scanner were among the dismissals.
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.
1,711 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, COMMAND_INJECTION_EVAL, FILE_MAGIC_MISMATCH and 3 more · Files: /repo/tests/fuzz/hookPayload.fuzz.test.ts, /repo/tests/helpers/phase-c-evidence.mjs, /repo/tests/unit/adapters/adapterParity.test.ts and 163 more · reported by cisco-skill-scanner
147 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, AAK-AGENT-003 · Files: AGENTS.md · reported by agent-audit-kit
107 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-005, AAK-LEGAL-002, AAK-HEALTHCARE-AI-004 and 4 more · Files: docs/releases/2.12.0.md, docs/releases/2.13.0.md, .github/workflows/publish-npm.yml and 75 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.
370 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/bin/ark-check-runtime.mjs, /repo/bin/ark-mcp-runtime.mjs, /repo/bin/ark-mcp.mjs and 81 more · reported by cisco-skill-scanner
68 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/bin/ark-check-runtime.mjs, /repo/bin/ark-mcp-runtime.mjs, /repo/bin/ark.mjs and 26 more · reported by cisco-skill-scanner
30 MANIFEST_MISSING_LICENSE
Files: /repo/.grok/skills/ark-coverage/SKILL.md, /repo/.grok/skills/ark-loop/SKILL.md, /repo/.grok/skills/ark-explain/SKILL.md and 27 more · reported by cisco-skill-scanner
19 HIDDEN_DATA_FILE
Files: /repo/.grok/skills/ark-upgrade/SKILL.md, /repo/.grok/skills/ark-fix/SKILL.md, /repo/.grok/workflows/product-beauty-audit.rhai and 15 more · reported by cisco-skill-scanner
16 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/eval/SKILL.md, /repo/packages/runtime/SKILL.md and 13 more · reported by cisco-skill-scanner
Critical command injection and sensitive data handling risks identified.
The artifact contains multiple critical command injection vulnerabilities in several files, including `bin/ark.mjs` and `bin/lib/github-enforcement.mjs`, which could lead to shell execution. It also handles sensitive PII data in `eval/causal/manifest.v1.json` and has a critical finding related to `AAK-MCP-015` in `bin/lib/resident-hook.mjs`. High severity findings indicate potential secret exposure and network egress capabilities, specifically `opt.nerlo-rules.nerlo-js-secret-to-network-egress`.
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.
10 AAK-HEALTHCARE-AI-004
Files: ROADMAP.md, eval/README.md, eval/causal/manifest.v1.json and 7 more · reported by agent-audit-kit
5 AAK-LEGAL-002
Files: eval/cases/enthusiast-greenfield-crud/package.json, eval/cases/next-core-imports-db/package.json, eval/cases/nest-entity-imports-repository/package.json and 2 more · reported by agent-audit-kit
4 LOW_ANALYZABILITY
Files: /repo/scripts/field-dogfood, /repo/eval, /repo and 1 more · reported by cisco-skill-scanner
3 DATA_EXFIL_JS_NETWORK
Files: /repo/eval/cases/domain-fetch-global/src/domain/remote.ts, /repo/scripts/verify-release-tag.mjs · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/eval/., /repo/. · reported by cisco-skill-scanner
2 hooks-no-stop-hooks
Files: settings.json, .claude/settings.json · reported by agentshield
2 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.grok/skills/ark-explain/SKILL.md, /repo/templates/skills/ark-explain.md · reported by nerlo-install-instruction
2 permissions-no-block
Files: settings.json, .claude/settings.json · reported by agentshield
1 AAK-HEALTHCARE-AI-005
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-INDIA-PII-001
Files: eval/causal/manifest.v1.json · reported by agent-audit-kit
1 AAK-MCP-015
Files: bin/lib/resident-hook.mjs · reported by agent-audit-kit
1 AAK-SECRET-004
Files: src/domain/effectiveContract.ts · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 AAK-TRUST-007
Files: .claude/settings.json · reported by agent-audit-kit
1 LAZY_LOAD_DEEP_NESTING
Files: /repo/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/scripts/verify-release-tag.mjs · reported by nerlo-behavioral
Showing 25 of 73; the rest are in the per-scanner reports above.