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.
168 critical findings reported by cisco-skill-scanner, agent-audit-kit, 149 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 -- comp
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
33 findings · 1.3s
v2.0.11
903 findings · 177.1s
v0.3.74
215 findings · 211.2s
v0.1.0
140 findings · 97.8s
v0.1.0
5 findings · 98.1s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 2.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
3 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 2, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
| Aug 8, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | rejected |
| Aug 2, 2026 | Flagged42 | — | agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit ·!: timeoutnerlo-behavioral ·!: timeoutnerlo-install-instruction ·!: timeoutnerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·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 1,296 findings across every scanner that examined this package. 16 of 168 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 238 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
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.
66 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: YARA_script_injection_generic, AAK-SECRET-003, AAK-SECRET-002 and 10 more · Files: /repo/apps/api/src/utils/file-type-validation.spec.ts, apps/api/src/cloud-security/evidence-sanitizer.spec.ts, apps/api/src/integration-platform/utils/redact-secrets.spec.ts and 20 more · reported by cisco-skill-scanner, agent-audit-kit
18 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: AAK-GHA-IMMUTABLE-001, permissions-no-block, hooks-no-pretooluse · Files: .github/workflows/database-migrations-release.yml, .github/workflows/auto-pr-to-release.yml, .github/workflows/security-questionnaire-extension-release.yml and 13 more · reported by agent-audit-kit, agentshield
8 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, ASSET_PROMPT_INJECTION, EXCESSIVE_FILE_COUNT · Files: /repo/packages/docs/images/browser-2fa-setup-key.png, /repo/packages/docs/images/enrollment-complete.png, /repo/packages/docs/openapi.json and 1 more · reported by cisco-skill-scanner
1 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: secrets-claude-md-env-2345 · Files: CLAUDE.md · reported by agentshield
The model could have called any of these a false positive and did not.
445 DATA_EXFIL_JS_NETWORK
Files: /repo/apps/api/src/admin-feature-flags/admin-feature-flags.service.ts, /repo/apps/api/src/background-checks/background-check-identity.client.ts, /repo/apps/api/src/browserbase/browser-mfa-instructions.service.ts and 128 more · reported by cisco-skill-scanner
136 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/packages/device-agent/src/checks/linux/antivirus.ts, /repo/packages/device-agent/src/checks/linux/disk-encryption.ts, /repo/packages/device-agent/src/checks/linux/screen-lock.ts and 21 more · reported by cisco-skill-scanner
127 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/apps/api/src/admin-feature-flags/admin-feature-flags.service.ts, /repo/apps/api/src/browserbase/browser-mfa-instructions.service.ts, /repo/apps/api/src/cloud-security/azure-command-executor.ts and 66 more · reported by nerlo-behavioral
64 AAK-TASKS-003
Files: apps/api/src/tasks/tasks.controller.ts, apps/api/src/tasks/tasks.service.ts, apps/api/src/tasks/tasks.module.ts and 61 more · reported by agent-audit-kit
43 AAK-SECRET-004
Files: integrations-catalog/integrations/socket.json, integrations-catalog/integrations/lob.json, packages/integration-platform/src/manifests/vercel/index.ts and 31 more
123 The review budget for this scan was already spent before these findings were reached.
Rules: EXCESSIVE_FILE_COUNT, HIDDEN_DATA_FILE, agents-no-model-agents/rbac-reviewer.md and 10 more · Files: /repo/apps/app/., /repo/.agents/skills/cursor-usage/SKILL.md, /repo/apps/app/.env.test.local.example and 104 more · reported by cisco-skill-scanner, agentshield, nerlo-behavioral and 1 more
106 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-SKILL-003, YARA_coercive_injection_generic, AAK-IPI-WILD-CORPUS-001 and 28 more · Files: .claude/skills/trigger-config/SKILL.md, .agents/skills/trigger-config/SKILL.md, /repo/SKILL.md and 86 more · reported by agent-audit-kit, cisco-skill-scanner, agentshield
9 The model did not answer for these findings.
Rules: AAK-LEGAL-002, SOCIAL_ENG_VAGUE_DESCRIPTION · Files: packages/docs/package.json, /repo/.github/SKILL.md, /repo/packages/docs/SKILL.md and 6 more · reported by agent-audit-kit, cisco-skill-scanner
Critical command injection and system modification risks identified.
The artifact contains critical command injection vulnerabilities, allowing arbitrary shell execution through JavaScript child processes and function constructors in files like `/repo/packages/db/scripts/generate-prisma-client-js.js` and `/repo/apps/app/src/lib/operator/dom.ts`. It also includes critical system modification capabilities via shell scripts, such as `/repo/packages/device-agent/assets/linux/after-install.sh`. Additionally, high-severity findings indicate potential secret exfiltration to the network and file system access, alongside medium-severity network egress. These capabilities warrant significant attention due to the potential for system compromise and data transmission.
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.
36 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/apps/api/scripts/encode-badge-icons.ts, /repo/apps/app/scripts/update-imports.js, /repo/packages/db/scripts/build-dist-schema.js and 5 more · reported by cisco-skill-scanner
17 LOW_ANALYZABILITY
Files: /repo/apps/app, /repo/apps/browser-extension/security-questionnaire-ext, /repo/apps/app/src/app/(app)/[orgId]/tasks/components and 14 more · reported by cisco-skill-scanner
16 AAK-LEGAL-002
Files: package.json, packages/db/package.json, packages/framework-editor-cli/package.json and 13 more · reported by agent-audit-kit
13 FILE_MAGIC_MISMATCH
Files: /repo/apps/app/src/app/(app)/[orgId]/tasks/[taskId]/automation/[automationId]/actions/prompts/automation-suggestions.ts, /repo/apps/app/src/trigger/tasks/onboarding/prompts/vendor-risk-assessment.ts, /repo/packages/integration-platform/src/task-mappings.ts and 4 more · reported by cisco-skill-scanner
10 HIDDEN_DATA_FILE
Files: /repo/apps/mcp-server/.speakeasy/gen.lock, /repo/apps/mcp-server/.speakeasy/out.openapi.yaml, /repo/apps/mcp-server/.dxtignore and 3 more · reported by cisco-skill-scanner
8 ASSET_PROMPT_INJECTION
Files: /repo/apps/mcp-server/.speakeasy/out.openapi.yaml, /repo/apps/mcp-server/manifest.json · reported by cisco-skill-scanner
7 EXCESSIVE_FILE_COUNT
Files: /repo/integrations-catalog/., /repo/apps/api/., /repo/packages/db/. and 4 more · reported by cisco-skill-scanner
4 AAK-MCP-018
Files: apps/mcp-server/src/mcp-server/tools.ts, apps/mcp-server/src/mcp-server/prompts.ts, apps/mcp-server/src/mcp-server/resources.ts and 1 more · reported by agent-audit-kit
4 AAK-MCP-ATTEST-001
Files: .mcp.json, .cursor/mcp.json, apps/app/.mcp.json · reported by agent-audit-kit
4 COMMAND_INJECTION_EVAL
Files: /repo/packages/ui/src/components/multiple-selector.tsx · reported by cisco-skill-scanner
4 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/apps/app/src/lib/operator/dom.ts, /repo/packages/integration-platform/src/dsl/interpreter.ts · reported by cisco-skill-scanner
4 TOOL_ABUSE_SYSTEM_MODIFICATION
Files: /repo/packages/device-agent/assets/linux/after-install.sh · reported by cisco-skill-scanner
4 UNANALYZABLE_BINARY
Files: /repo/packages/device-agent/assets/icon.icns, /repo/apps/app/public/pulse.mp3 · reported by cisco-skill-scanner
3 AAK-AGENT-SHARED-RES-AUTHZ-001
Files: packages/db/prisma/seed/primitives/FrameworkEditorTaskTemplate.json, packages/db/prisma/seed/primitives/FrameworkEditorRequirement.json · reported by agent-audit-kit
3 AAK-MCP-005
Files: .mcp.json, .cursor/mcp.json · reported by agent-audit-kit
2 AAK-MCP-HTTP-NOAUTH-SERVER-001
Files: apps/mcp-server/src/mcp-server/cli/start/impl.ts, apps/mcp-server/src/mcp-server/cli/serve/impl.ts · reported by agent-audit-kit
2 AAK-OAUTH-005
Files: packages/integration-platform/src/runtime/check-context.ts, apps/api/src/auth/hybrid-auth.guard.ts · reported by agent-audit-kit
2 AAK-SPLUNK-TOKLOG-001
Files: apps/api/src/auth/api-key.service.ts, apps/app/src/lib/api-key.ts · reported by agent-audit-kit
2 YARA_capability_inflation_generic
Files: /repo/apps/app/src/app/(app)/setup/components/AnimatedGradientBackground.tsx · reported by cisco-skill-scanner
1 AAK-MCP-001
Files: apps/app/.mcp.json · reported by agent-audit-kit
1 AAK-OAUTH-006
Files: apps/api/src/integration-platform/controllers/oauth.controller.ts · reported by agent-audit-kit
1 AAK-SUPPLY-003
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: package.json · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/apps/app/src/lib/operator/dom.ts · reported by nerlo-behavioral
Showing 25 of 392; the rest are in the per-scanner reports above.