@codemieai/code · Nerlo

@codemieai/code

Version: v0.12.0
By: AI/Run Team
License: Apache-2.0
Last scan: Scanned Sep 3, 2026, 5:45 PM UTC

MCP Server

Scan Haltedcomposite

Unified AI coding assistant CLI - Manage Claude Code, Gemini & custom agents. Multi-provider support (OpenAI, Azure, LiteLLM, SSO). Built-in LangGraph agent with file operations & git integration.

Source:: github.com/codemie-ai/codemie-code
Version:: 0.12.0
License:: Apache-2.0
Author:: AI/Run Team
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.

225 critical findings reported by cisco-skill-scanner, agent-audit-kit, 134 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.

This artifact ships from 2 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/codemie-ai/codemie-code, 791 findings

Install

Choose your runtime: the CLI writes the mcpServers config entry for that target.

nerlo install --target claude-code -- @codemieai/code

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
Clean97
- 6Med
6 findings · 1.0s

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: 429
Dismissed as false positives: 350
Not reviewed: 12

Out of 791 findings across every scanner that examined this package. 79 of 225 findings rated critical by their scanner were among the dismissals.

Not reviewed is not the same as clean. Those 12 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.

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.

181 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, COMMAND_INJECTION_EVAL, AAK-INDIA-PII-001 and 13 more · Files: /repo/tests/helpers/agent-smoke.ts, /repo/tests/integration/agent-assistant.test.ts, /repo/tests/integration/agent-codex.test.ts and 48 more · reported by cisco-skill-scanner, agent-audit-kit
155 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: PIPELINE_TAINT_FLOW, YARA_system_manipulation_generic, opt.nerlo-rules.nerlo-install-pipe-to-shell and 8 more · Files: /repo/docs/specs/claude-version-management/installation-and-versioning.md, /repo/docs/superpowers/tasks/2026-08-25-profile-provider-decoupling/lens-edge-case.json, AGENTS.md and 77 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
13 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, AAK-AGENT-001 · Files: AGENTS.md, CLAUDE.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

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.

80 COMMAND_INJECTION_EVAL
Files: /repo/install/chrome/epam-airun-codemie-0.3.3.zip!/assets/panel-DsKm38iR.js, /repo/src/agents/core/BaseAgentAdapter.ts, /repo/src/agents/plugins/claude/claude.plugin.ts and 28 more · reported by cisco-skill-scanner
66 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/src/cli/commands/assistants/setup/generators/claude-agent-generator.ts, /repo/src/cli/commands/assistants/setup/generators/claude-skill-generator.ts, /repo/src/cli/commands/assistants/setup/generators/codex-skill-generator.ts and 18 more · reported by cisco-skill-scanner
46 DATA_EXFIL_JS_NETWORK
Files: /repo/src/agents/plugins/claude/plugin/skills/msgraph/scripts/msgraph.js, /repo/src/agents/plugins/claude/plugin/skills/codemie-analytics/scripts/analytics-cli.js, /repo/install/chrome/epam-airun-codemie-0.3.3.zip!/assets/index.ts-BP-QOFTR.js and 15 more · reported by cisco-skill-scanner
37 HIDDEN_DATA_FILE
Files: /repo/openwiki/.claims/integrations/agent-plugin-system.json, /repo/.ai-run/guides/standards/code-quality.md, /repo/.openwikiignore and 23 more · reported by cisco-skill-scanner
35 MANIFEST_MISSING_LICENSE

Not reviewed

12 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-SECRET-002 · Files: src/utils/__tests__/security.test.ts · reported by agent-audit-kit

What the review concluded

Critical risks: command injection, secret exposure, and script injection

The artifact contains numerous instances of potential command injection, specifically `COMMAND_INJECTION_EVAL` and `COMMAND_INJECTION_JS_CHILD_PROCESS`, which could lead to shell execution. Several critical secrets, including Google API keys, are present in files such as `/repo/install/chrome/epam-airun-codemie-0.3.3.zip!/assets/index.ts-BP-QOFTR.js` and `src/utils/__tests__/security.test.ts`. Additionally, there are multiple findings related to generic script injection and data tainting, indicating potential vulnerabilities for arbitrary code execution or data manipulation. These issues collectively present a significant risk to the environment where the artifact operates.

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

What to look at

AAK-MCP-015 · src/agents/plugins/claude/plugin/skills/msgraph/scripts/msgraph.js · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/providers/plugins/sso/sso.auth.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/providers/plugins/sso/sso.auth.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/providers/plugins/sso/sso.auth.ts · critical · reported by agent-audit-kit
AAK-SECRET-002 · src/utils/__tests__/security.test.ts · critical · reported by agent-audit-kit
AAK-SECRET-002 · src/utils/__tests__/security.test.ts · critical · reported by agent-audit-kit
· · 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

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

Completed	Composite	Change	Scanners	Status
Sep 3, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete	rejected
Aug 11, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable	rejected

Per-scanner history:

AI review of these findings

Upheld as real: 429
Dismissed as false positives: 350
Not reviewed: 12

Out of 791 findings across every scanner that examined this package. 79 of 225 findings rated critical by their scanner were among the dismissals.

Not reviewed is not the same as clean. Those 12 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.

Why those were dismissed

181 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, COMMAND_INJECTION_EVAL, AAK-INDIA-PII-001 and 13 more · Files: /repo/tests/helpers/agent-smoke.ts, /repo/tests/integration/agent-assistant.test.ts, /repo/tests/integration/agent-codex.test.ts and 48 more · reported by cisco-skill-scanner, agent-audit-kit
155 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: PIPELINE_TAINT_FLOW, YARA_system_manipulation_generic, opt.nerlo-rules.nerlo-install-pipe-to-shell and 8 more · Files: /repo/docs/specs/claude-version-management/installation-and-versioning.md, /repo/docs/superpowers/tasks/2026-08-25-profile-provider-decoupling/lens-edge-case.json, AGENTS.md and 77 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
13 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, AAK-AGENT-001 · Files: AGENTS.md, CLAUDE.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

In installed code — never dismissed

80 COMMAND_INJECTION_EVAL
Files: /repo/install/chrome/epam-airun-codemie-0.3.3.zip!/assets/panel-DsKm38iR.js, /repo/src/agents/core/BaseAgentAdapter.ts, /repo/src/agents/plugins/claude/claude.plugin.ts and 28 more · reported by cisco-skill-scanner
66 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/src/cli/commands/assistants/setup/generators/claude-agent-generator.ts, /repo/src/cli/commands/assistants/setup/generators/claude-skill-generator.ts, /repo/src/cli/commands/assistants/setup/generators/codex-skill-generator.ts and 18 more · reported by cisco-skill-scanner
46 DATA_EXFIL_JS_NETWORK
Files: /repo/src/agents/plugins/claude/plugin/skills/msgraph/scripts/msgraph.js, /repo/src/agents/plugins/claude/plugin/skills/codemie-analytics/scripts/analytics-cli.js, /repo/install/chrome/epam-airun-codemie-0.3.3.zip!/assets/index.ts-BP-QOFTR.js and 15 more · reported by cisco-skill-scanner
37 HIDDEN_DATA_FILE
Files: /repo/openwiki/.claims/integrations/agent-plugin-system.json, /repo/.ai-run/guides/standards/code-quality.md, /repo/.openwikiignore and 23 more · reported by cisco-skill-scanner
35 MANIFEST_MISSING_LICENSE

Not reviewed

12 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-SECRET-002 · Files: src/utils/__tests__/security.test.ts · reported by agent-audit-kit

What the review concluded

Critical risks: command injection, secret exposure, and script injection

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

What to look at

AAK-MCP-015 · src/agents/plugins/claude/plugin/skills/msgraph/scripts/msgraph.js · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/providers/plugins/sso/sso.auth.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/providers/plugins/sso/sso.auth.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/providers/plugins/sso/sso.auth.ts · critical · reported by agent-audit-kit
AAK-SECRET-002 · src/utils/__tests__/security.test.ts · critical · reported by agent-audit-kit
AAK-SECRET-002 · src/utils/__tests__/security.test.ts · critical · reported by agent-audit-kit
· · 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.

@codemieai/code

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

Not reviewed

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

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

Not reviewed

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at