Loading the registry…
MCP-Bastion monorepo: security middleware for MCP servers
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.
27 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 -- mcp-bastion
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
1 finding · 0.5s
v2.0.11
280 findings · 92.8s
v0.3.26
57 findings · 22.2s
v0.1.0
2 findings · 31.7s
v0.1.0
0 findings · 31.7s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 11.9s
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 340 findings across every scanner that examined this package. 23 of 27 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 5 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.
139 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_generic, PDF_STRUCTURAL_THREAT, AAK-IPI-WILD-CORPUS-001 and 14 more · Files: /repo/examples/fixtures/tools-poisoned.json, /repo/docs/site/assets/mcp-bastian-features-deck.pdf, /repo/docs/MCP-Bastion-2.0.0-LinkedIn-Deck.pdf and 42 more · reported by cisco-skill-scanner, agent-audit-kit
21 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-SECRET-003, COMMAND_INJECTION_EVAL, YARA_sql_injection_generic and 8 more · Files: tests/test_top10_controls.py, tests/test_policy_simulator.py, tests/test_schema_strict_and_pdf.py and 12 more · reported by agent-audit-kit, cisco-skill-scanner
9 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, hooks-no-pretooluse, MANIFEST_INVALID_NAME · Files: .github/workflows/publish-mcp.yml, .github/workflows/publish-integrations.yml, .github/workflows/publish-docker.yml and 2 more · reported by agent-audit-kit, agentshield, 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.
28 DATA_EXFIL_JS_NETWORK
Files: /repo/dashboard/static/dashboard-app.js, /repo/packages/core/src/guard.ts · reported by cisco-skill-scanner
25 YARA_prompt_injection_unicode_steganography
Files: /repo/dashboard/static/mcp-bastian.png, /repo/images/dashboard-demo/raw/10-drift.png, /repo/images/deshboard-walkthrow.gif and 4 more · reported by cisco-skill-scanner
24 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/scripts/census_public_mcp.py, /repo/scripts/dispatch_integrations_workflow.py, /repo/scripts/verify_package_registries.py and 8 more · reported by cisco-skill-scanner
22 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/deploy/SKILL.md, /repo/dashboard/SKILL.md and 19 more · reported by cisco-skill-scanner
22 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/deploy/SKILL.md, /repo/dashboard/SKILL.md and 19 more · reported by cisco-skill-scanner
5 The model did not answer for these findings.
Rules: SECRET_PASSWORD_VAR · Files: /repo/tests/test_runtime_governance_e2e.py · reported by cisco-skill-scanner
Artifact contains command injection and exposed secrets.
The artifact includes code that allows for command injection in `/repo/src/mcp_bastion/pillars/content_filter.py` and `/repo/src/mcp_bastion/pillars/prompt_guard.py`. It also exposes a critical secret in `src/mcp_bastion/redteam.py`. Additionally, several high-severity findings indicate other secrets are present in various files, and the artifact may perform network egress with these secrets.
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.
9 PROMPT_INJECTION_IGNORE_INSTRUCTIONS
Files: /repo/README.md, /repo/SKILL.md, /repo/VALIDATION_CHECKLIST.md · reported by cisco-skill-scanner
7 AAK-SECRET-004
Files: scripts/dispatch_integrations_workflow.py, src/mcp_bastion/cli.py, src/mcp_bastion/otel.py and 2 more · reported by agent-audit-kit
4 AAK-MCP-018
Files: scripts/build_docs_site.py, scripts/generate_linkedin_deck.py, src/mcp_bastion/transport_hardening.py and 1 more · reported by agent-audit-kit
3 COMMAND_INJECTION_EVAL
Files: /repo/src/mcp_bastion/pillars/content_filter.py, /repo/src/mcp_bastion/pillars/prompt_guard.py · reported by cisco-skill-scanner
2 AAK-IPI-WILD-CORPUS-001
Files: SETUP_GUIDE.md, src/mcp_bastion/benchmarks/injection_efficacy.py · reported by agent-audit-kit
2 AAK-MCP-STATELESS-001
Files: src/mcp_bastion/mcp_transport.py, src/mcp_bastion/proxy_server.py · reported by agent-audit-kit
2 LOW_ANALYZABILITY
Files: /repo/dashboard, /repo/packages/core · reported by cisco-skill-scanner
1 AAK-DNS-REBIND-002
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-HEALTHCARE-AI-005
Files: README.md · reported by agent-audit-kit
1 AAK-MCP-STATELESS-004
Files: src/mcp_bastion/proxy_server.py · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-SECRET-003
Files: src/mcp_bastion/redteam.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 DATA_EXFIL_SOCKET_CONNECT
Files: /repo/src/mcp_bastion/otel.py · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
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/dashboard/static/dashboard-app.js · reported by nerlo-behavioral
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/scripts/dispatch_integrations_workflow.py · reported by nerlo-behavioral
1 OVERSIZED_FILE
Files: /repo/images/dashboard-demo/raw/full-page.png · reported by cisco-skill-scanner
1 PROMPT_INJECTION_REVEAL_SYSTEM
Files: /repo/SETUP_GUIDE.md · reported by cisco-skill-scanner
1 SOCIAL_ENG_ANTHROPIC_IMPERSONATION
Files: /repo/integrations/mcp-bastion-anthropic/SKILL.md · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md · reported by cisco-skill-scanner
1 UNANALYZABLE_BINARY
Files: /repo/MCP-Security-Deck-v3.pdf · reported by cisco-skill-scanner
Showing 25 of 28; the rest are in the per-scanner reports above.