Send and receive emails from any agent.
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.
16 critical findings reported by cisco-skill-scanner, agent-audit-kit, 4 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 -- mcpemails-monorepo
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 · 0.7s
v2.0.11
149 findings · 22.1s
v0.3.74
62 findings · 14.7s
v0.1.0
38 findings · 47.5s
v0.1.0
2 findings · 47.5s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image, nerlo-multi-source.
7 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 16, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | rejected |
| Aug 4, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | rejected |
| Aug 3, 2026 | Flagged20 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·n/a: not applicable | completed |
| Aug 1, 2026 | Flagged16 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: complete | completed |
| Jul 31, 2026 | Flagged16 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·n/a: not applicable | completed |
| Jul 30, 2026 | Flagged7 | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·n/a: not applicable | completed |
| Jul 29, 2026 | Flagged16 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-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 251 findings across every scanner that examined this package. 12 of 16 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.
14 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-INDIA-PII-001, COMMAND_INJECTION_JS_CHILD_PROCESS, YARA_script_injection_generic and 2 more · Files: supabase/functions/mcp-server/mcp-app-bulk.test.ts, supabase/functions/mcp-server/mcp-app-approvals.test.ts, /repo/apps/web/scripts/gsc-indexing-report.test.mjs and 2 more · reported by agent-audit-kit, cisco-skill-scanner
10 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE, opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: /repo/docs/SKILL.md, /repo/docs/usage-based-pricing/SKILL.md, /repo/docs/synthetic-monitoring/SKILL.md and 2 more · reported by cisco-skill-scanner, nerlo-install-instruction
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.
91 DATA_EXFIL_JS_NETWORK
Files: /repo/apps/web/app/api/inboxes/[id]/route.ts, /repo/apps/web/app/api/mcp/route.ts, /repo/apps/web/components/admin/MetricDrawer.tsx and 13 more · reported by cisco-skill-scanner
24 AAK-SECRET-004
Files: self-host/cli/mcpe.ts, apps/web/messages/en/dashboardChrome.json, apps/web/messages/nb/docs.json and 12 more · reported by agent-audit-kit
24 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/apps/web/app/api/inboxes/[id]/route.ts, /repo/apps/web/app/api/mcp/route.ts, /repo/apps/web/src/lib/email-providers/gmail.ts and 4 more · reported by nerlo-behavioral
19 AAK-OAUTH-005
Files: apps/web/src/lib/blog/posts/email-for-ai-agents-cursor-cline-vscode.js, apps/web/src/lib/blog/posts/oauth-vs-api-keys-ai-email-access.js, apps/web/src/lib/blog/posts/build-email-auto-responder-mcp-agent.js and 16 more · reported by agent-audit-kit
14 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files:
Critical script injection and secret exposure detected.
The artifact contains critical script injection vulnerabilities in `/repo/apps/mcp-app/harness/fixtures.mjs` and `/repo/supabase/functions/mcp-server/index.ts`, which could lead to arbitrary code execution. Additionally, numerous hardcoded secrets are present across various files, including API routes and server functions, potentially enabling credential access. The artifact also exhibits network egress capabilities from JavaScript code that handles secrets, and contains hidden executable scripts.
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.
11 HIDDEN_DATA_FILE
Files: /repo/supabase/.temp/postgres-version, /repo/supabase/.temp/project-ref, /repo/apps/web/.thumbnail and 8 more · reported by cisco-skill-scanner
10 FILE_MAGIC_MISMATCH
Files: /repo/apps/web/app/(auth)/login/page.js, /repo/apps/web/app/approvals/[id]/page.js, /repo/apps/web/app/authorize/page.js and 7 more · reported by cisco-skill-scanner
5 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/apps/web/app/.well-known/glama.json/route.ts, /repo/apps/web/app/.well-known/oauth-protected-resource/[...resource]/route.ts, /repo/apps/web/app/.well-known/oauth-protected-resource/route.ts and 2 more · reported by cisco-skill-scanner
3 YARA_script_injection_generic
Files: /repo/apps/mcp-app/harness/fixtures.mjs · reported by cisco-skill-scanner
2 AAK-LEGAL-002
Files: apps/mcp-app/package.json, apps/web/package.json · reported by agent-audit-kit
2 ASSET_PROMPT_INJECTION
Files: /repo/apps/web/messages/en/auth.json, /repo/apps/web/messages/es/auth.json · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/scripts/stripe-setup.js · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/self-host, /repo · reported by cisco-skill-scanner
2 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/self-host/SKILL.md · reported by cisco-skill-scanner
2 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/self-host/SKILL.md · reported by cisco-skill-scanner
2 YARA_capability_inflation_generic
Files: /repo/supabase/functions/mcp-server/index.ts · reported by cisco-skill-scanner
2 YARA_indirect_prompt_injection_generic
Files: /repo/apps/web/messages/en/docs.json · reported by cisco-skill-scanner
1 AAK-LEGAL-001
Files: package.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: apps/mcp-app/harness/fixture-server.mjs · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: apps/web/src/lib/oauth/state.ts · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-SPLUNK-TOKLOG-001
Files: supabase/functions/mcp-server/index.ts · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 BINARY_FILE_DETECTED
Files: /repo/apps/web/.thumbnail · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 UNANALYZABLE_BINARY
Files: /repo/apps/web/.thumbnail · reported by cisco-skill-scanner
1 YARA_coercive_injection_generic
Files: /repo/supabase/functions/mcp-server/index.ts · reported by cisco-skill-scanner
Showing 25 of 50; the rest are in the per-scanner reports above.