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.
70 critical findings reported by cisco-skill-scanner, agent-audit-kit, 40 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- unified-ai-system
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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
433 findings · 44.0s
v0.3.26
83 findings · 19.5s
v0.1.0
44 findings · 73.9s
v0.1.0
0 findings · 74.0s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 12.1s
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 ·n/a: not applicable | rejected |
| Jul 31, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·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 560 findings across every scanner that examined this package. 30 of 70 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.
90 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_EVAL, AAK-SECRET-003, AAK-MCP-MARKETPLACE-CONFIG-FETCH-001 and 8 more · Files: /repo/packages/forge-core/test/e2e-health-review.test.js, /repo/packages/forge-core/test/p11-quality-gate.test.js, /repo/packages/forge-core/test/p7-review-stream-part1.test.js and 31 more · reported by cisco-skill-scanner, agent-audit-kit
16 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-js-secret-to-network-egress, FILE_MAGIC_MISMATCH, HIDDEN_DATA_FILE and 3 more · Files: /repo/docs/examples/javascript-chat.mjs, /repo/docs/llms.txt, /repo/docs/.nojekyll and 6 more · reported by nerlo-behavioral, cisco-skill-scanner
14 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 · Files: AGENTS.md · reported by agent-audit-kit
1 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: MANIFEST_INVALID_NAME · Files: /repo/.github/SKILL.md · reported by cisco-skill-scanner
1 Placeholder value — The matched literal is a placeholder or example — the kind of value a scanner reads as a secret and a human reads as a blank to fill in.
Rules: HIDDEN_DATA_FILE · Files: /repo/.env.enterprise.example · 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.
98 DATA_EXFIL_JS_NETWORK
Files: /repo/apps/ai-gateway-service/src/alerting/alertEngine.js, /repo/apps/ai-gateway-service/src/automation/commandPaletteProviderHandlers.js, /repo/apps/ai-gateway-service/src/capabilities/godReviewCellExecutor-gateway.js and 32 more · reported by cisco-skill-scanner
73 FILE_MAGIC_MISMATCH
Files: /repo/apps/agent-console/src/index.js, /repo/packages/employee-brain-adapter/src/index.js, /repo/packages/forge-core/src/chaos-engineer/index.js and 44 more · reported by cisco-skill-scanner
60 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/apps/ai-gateway-service/src/automation/commandPaletteBillingHandlers.js, /repo/apps/ai-gateway-service/src/automation/commandPaletteMiscHandlers.js, /repo/apps/ai-gateway-service/src/automation/commandPaletteSecurityHandlers.js and 12 more · reported by cisco-skill-scanner
30 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/apps/ai-gateway-service/src/capabilities/godReviewCellExecutor-gateway.js, /repo/apps/ai-gateway-service/src/capabilities/tianshuPlannerStorage.js, /repo/apps/ai-gateway-service/src/enterprise/oauth2Provider.js and 12 more · reported by nerlo-behavioral
29
Artifact has critical command execution and data exfiltration risks.
The artifact contains numerous instances of potential command injection via child processes and `eval` in files like `neuronCodeGenerator.js` and `forge-core`. It also exhibits capabilities for credential access and network egress, with secrets potentially exposed and data exfiltration from the clipboard. These findings indicate the artifact can execute arbitrary code and transmit sensitive information.
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: packages/forge-core/start-server.mjs, packages/forge-core/src/index.js, packages/forge-core/src/checkpoint/index.js and 26 more · reported by agent-audit-kit
20 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/apps/ai-gateway-service/src/claude-code-patterns/builtInCoreTools.js, /repo/packages/forge-core/src/checkpoint/index.js, /repo/packages/forge-core/src/verification/helpers.js and 5 more · reported by cisco-skill-scanner
20 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/packages/im-connector-feishu/SKILL.md, /repo/packages/im-connector-wecom/SKILL.md and 17 more · reported by cisco-skill-scanner
20 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/packages/im-connector-feishu/SKILL.md, /repo/packages/im-connector-wecom/SKILL.md and 17 more · reported by cisco-skill-scanner
17 AAK-LEGAL-002
Files: packages/im-connector-feishu/package.json, packages/im-connector-wecom/package.json, packages/workforce-contracts/package.json and 14 more · reported by agent-audit-kit
17 LOW_ANALYZABILITY
Files: /repo/packages/forge-core/src/memory-engine, /repo/packages/codex-context-gateway, /repo/packages/shared-contracts and 14 more · reported by cisco-skill-scanner
15 COMMAND_INJECTION_EVAL
Files: /repo/apps/ai-gateway-service/src/capabilities/neuronCodeGenerator.js, /repo/apps/ai-gateway-service/src/capabilities/safetyScanner.js, /repo/packages/forge-core/src/quality-gate/helpers.js and 4 more · reported by cisco-skill-scanner
12 opt.nerlo-rules.nerlo-clipboard-read-exfiltration
Files: /repo/apps/ai-gateway-service/src/entrypoints/benchmarkUtils.js · reported by nerlo-behavioral
5 AAK-SECRET-004
Files: packages/codex-context-gateway/src/redactedConfigPreviewBuilder.js, packages/codex-context-gateway/src/promptPackLoader.js, apps/ai-gateway-service/src/enterprise/apiKeyManager.js and 2 more · reported by agent-audit-kit
4 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/packages/forge-core/src/skills/skillInstaller.js, /repo/packages/forge-core/src/verification/helpers.js · reported by cisco-skill-scanner
4 HIDDEN_DATA_FILE
Files: /repo/.agents/plugins/marketplace.json, /repo/.codex-plugin/plugin.json, /repo/.codexignore and 1 more · reported by cisco-skill-scanner
3 AAK-OAUTH-001
Files: packages/forge-core/src/integration/auth-adapter.js, apps/ai-gateway-service/src/http/httpServer.js, apps/ai-gateway-service/src/enterprise/enterpriseGovernanceService.js · reported by agent-audit-kit
3 EXCESSIVE_FILE_COUNT
Files: /repo/packages/forge-core/., /repo/., /repo/packages/codex-context-gateway/. · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-001
Files: .agents/plugins/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: tools/verify-public-clone.mjs · reported by agent-audit-kit
1 AAK-MCPFRAME-001
Files: packages/forge-core/src/integration/forge-routes.js · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-001
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-002
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-003
Files: PRIVACY.md · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/apps/ai-gateway-service/src/tools/webSearchTool.js · reported by nerlo-behavioral
1 YARA_prompt_injection_generic
Files: /repo/apps/ai-gateway-service/src/claude-code-patterns/sandboxTools.js · reported by cisco-skill-scanner
Showing 25 of 91; the rest are in the per-scanner reports above.