create-byan-agent · Nerlo

create-byan-agent

Name: create-byan-agent
Author: Yan

Version: v2.60.1
By: Yan
License: MIT
Last scan: Scanned Aug 22, 2026, 10:38 AM UTC

Claude Skill

Scan Haltedcomposite

BYAN v2.8 - Intelligent AI agent creator with ELO trust system + scientific fact-check + Hermes universal dispatcher + native Claude Code integration (hooks, skills, MCP server). Multi-platform (Claude Code, Codex). Merise Agile + TDD + 71 Mantras. ~54% LLM cost savings.

Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.

Source:: github.com/yan-acadenice/byan
Version:: 2.60.1
License:: MIT
Author:: Yan
Provenance:: Found by crawling (provenance, not a security rating)

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.

296 critical findings reported by cisco-skill-scanner, agent-audit-kit, 225 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/yan-acadenice/byan, 4776 findings

Install

Claude Skills install to a single target, no runtime picker.

nerlo install -- create-byan-agent

Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.

cp -r -- create-byan-agent ~/.claude/skills/

Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.

How scores work Full audit report

Per-scanner reports

7 scanners

Your view:

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.

Scanners that examined this package (6)

agentshield
v1.4.0
Caution77
- 105High
- 7Med
- 6Info
118 findings · 1.5s

AI review of these findings

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.

Upheld as real: 2,483
Dismissed as false positives: 813
Not reviewed: 0

Out of 3,296 findings across every scanner that examined this package. 71 of 296 findings rated critical by their scanner were among the dismissals.

Why those were dismissed

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.

696 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, YARA_command_injection_generic, YARA_credential_harvesting_generic and 9 more · Files: /repo/.claude/__tests__/autobench-ledger-report.test.js, /repo/.claude/__tests__/autobench-stop-guard.test.js, /repo/.claude/__tests__/fact-check-claims.test.js and 102 more · reported by cisco-skill-scanner, nerlo-behavioral, agent-audit-kit
104 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_system_manipulation_generic, SOCIAL_ENG_VAGUE_DESCRIPTION, opt.nerlo-rules.nerlo-install-run-bundled-artifact and 2 more · Files: /repo/docs/archive/copilot-sdk/COPILOT-AGENTS-UPDATE-v1.1.0.md, /repo/.github/SKILL.md, /repo/docs/SKILL.md and 27 more · reported by cisco-skill-scanner, nerlo-install-instruction
11 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-005, secrets-base64-obfuscation-4378 · Files: AGENTS.md, .claude/CLAUDE.md, app/CLAUDE.md · reported by agent-audit-kit, agentshield
2 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 · Files: .github/workflows/electron-build.yml, .github/workflows/yanstaller-test.yml · reported by agent-audit-kit

In installed code — never dismissed

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.

885 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/.claude/hooks/agent-gate-check.js, /repo/.claude/hooks/codex-autodelegate.js, /repo/.claude/hooks/fd-phase-guard.js and 180 more · reported by cisco-skill-scanner
467 MANIFEST_MISSING_LICENSE
Files: /repo/.codex/skills/byan/SKILL.md, /repo/.claude/skills/byan-byan/SKILL.md, /repo/.claude/skills/byan-drawio/SKILL.md and 464 more · reported by cisco-skill-scanner
258 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.claude/skills/byan-byan/SKILL.md, /repo/.claude/skills/byan-orchestrate/SKILL.md, /repo/.claude/skills/byan-merise-agile/SKILL.md and 255 more · reported by cisco-skill-scanner
222 FILE_MAGIC_MISMATCH
Files: /repo/.claude/skills/byan-cis-creative-problem-solver/SKILL.md, /repo/.claude/skills/byan-cis-brainstorming-coach/SKILL.md, /repo/.claude/skills/byan-bmm-dev/SKILL.md and 46 more · reported by cisco-skill-scanner
200 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/.claude/hooks/codex-delegate-guard.js, /repo/.claude/hooks/mantra-validate.js, /repo/.claude/hooks/pre-compact-save.js and 47 more

Upheld — the review declined to dismiss these

The model could have called any of these a false positive and did not.

5 OBFUSCATION_XOR_ENCODING
Files: /repo/_byan/mcp/byan-mcp-server/bin/byan-build-skill-bundles.js, /repo/install/templates/_byan/mcp/byan-mcp-server/bin/byan-build-skill-bundles.js · reported by cisco-skill-scanner

What the review concluded

Artifact exhibits critical command injection and data exfiltration risks.

The artifact contains numerous critical findings related to command injection via child processes and `eval` in multiple JavaScript files, including those handling inter-process communication and server logic. It also shows critical vulnerabilities for DNS rebinding and server-side request forgery. Additionally, there are high-severity findings indicating potential for file system access and network egress of sensitive data.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

AAK-DNS-REBIND-001 · _byan/mcp/byan-mcp-server/server-http.js · critical · reported by agent-audit-kit
AAK-MCP-STDIO-CMD-INJ-002 · _byan/mcp/byan-mcp-server/server.js · critical · reported by agent-audit-kit
AAK-SSRF-001 · app/shared/ipc-contract.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · app/shared/ipc-contract.ts · critical · reported by agent-audit-kit
AAK-MCP-015 · install/src/webui/server.js · critical · reported by agent-audit-kit
AAK-DNS-REBIND-001 · install/templates/_byan/mcp/byan-mcp-server/server-http.js · critical · reported by agent-audit-kit
AAK-MCP-STDIO-CMD-INJ-002 · install/templates/_byan/mcp/byan-mcp-server/server.js · critical · reported by agent-audit-kit

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

Scan history

1 scan on record. Every scan's full results are retained immutably for 24 months.

Completed	Composite	Change	Scanners	Status
Aug 22, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete	rejected

Per-scanner history:

AI review of these findings

Upheld as real: 2,483
Dismissed as false positives: 813
Not reviewed: 0

Out of 3,296 findings across every scanner that examined this package. 71 of 296 findings rated critical by their scanner were among the dismissals.

Why those were dismissed

696 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, YARA_command_injection_generic, YARA_credential_harvesting_generic and 9 more · Files: /repo/.claude/__tests__/autobench-ledger-report.test.js, /repo/.claude/__tests__/autobench-stop-guard.test.js, /repo/.claude/__tests__/fact-check-claims.test.js and 102 more · reported by cisco-skill-scanner, nerlo-behavioral, agent-audit-kit
104 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_system_manipulation_generic, SOCIAL_ENG_VAGUE_DESCRIPTION, opt.nerlo-rules.nerlo-install-run-bundled-artifact and 2 more · Files: /repo/docs/archive/copilot-sdk/COPILOT-AGENTS-UPDATE-v1.1.0.md, /repo/.github/SKILL.md, /repo/docs/SKILL.md and 27 more · reported by cisco-skill-scanner, nerlo-install-instruction
11 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-005, secrets-base64-obfuscation-4378 · Files: AGENTS.md, .claude/CLAUDE.md, app/CLAUDE.md · reported by agent-audit-kit, agentshield
2 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 · Files: .github/workflows/electron-build.yml, .github/workflows/yanstaller-test.yml · reported by agent-audit-kit

In installed code — never dismissed

885 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/.claude/hooks/agent-gate-check.js, /repo/.claude/hooks/codex-autodelegate.js, /repo/.claude/hooks/fd-phase-guard.js and 180 more · reported by cisco-skill-scanner
467 MANIFEST_MISSING_LICENSE
Files: /repo/.codex/skills/byan/SKILL.md, /repo/.claude/skills/byan-byan/SKILL.md, /repo/.claude/skills/byan-drawio/SKILL.md and 464 more · reported by cisco-skill-scanner
258 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.claude/skills/byan-byan/SKILL.md, /repo/.claude/skills/byan-orchestrate/SKILL.md, /repo/.claude/skills/byan-merise-agile/SKILL.md and 255 more · reported by cisco-skill-scanner
222 FILE_MAGIC_MISMATCH
Files: /repo/.claude/skills/byan-cis-creative-problem-solver/SKILL.md, /repo/.claude/skills/byan-cis-brainstorming-coach/SKILL.md, /repo/.claude/skills/byan-bmm-dev/SKILL.md and 46 more · reported by cisco-skill-scanner
200 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/.claude/hooks/codex-delegate-guard.js, /repo/.claude/hooks/mantra-validate.js, /repo/.claude/hooks/pre-compact-save.js and 47 more

Upheld — the review declined to dismiss these

The model could have called any of these a false positive and did not.

5 OBFUSCATION_XOR_ENCODING
Files: /repo/_byan/mcp/byan-mcp-server/bin/byan-build-skill-bundles.js, /repo/install/templates/_byan/mcp/byan-mcp-server/bin/byan-build-skill-bundles.js · reported by cisco-skill-scanner

What the review concluded

Artifact exhibits critical command injection and data exfiltration risks.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

AAK-DNS-REBIND-001 · _byan/mcp/byan-mcp-server/server-http.js · critical · reported by agent-audit-kit
AAK-MCP-STDIO-CMD-INJ-002 · _byan/mcp/byan-mcp-server/server.js · critical · reported by agent-audit-kit
AAK-SSRF-001 · app/shared/ipc-contract.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · app/shared/ipc-contract.ts · critical · reported by agent-audit-kit
AAK-MCP-015 · install/src/webui/server.js · critical · reported by agent-audit-kit
AAK-DNS-REBIND-001 · install/templates/_byan/mcp/byan-mcp-server/server-http.js · critical · reported by agent-audit-kit
AAK-MCP-STDIO-CMD-INJ-002 · install/templates/_byan/mcp/byan-mcp-server/server.js · critical · reported by agent-audit-kit

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

create-byan-agent

Install

Per-scanner reports

Scanners that examined this package (6)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

nerlo-multi-source

Scanners that did not run on this package (5)

capslock

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Install

Per-scanner reports

Scanners that examined this package (6)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

nerlo-multi-source

Scanners that did not run on this package (5)

capslock

Composite scoreOne view among many — the per-scanner reports above are primaryScan Halted

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at