Loading the registry…
Codey — a multi-agent workbench and control plane for coding agents (Claude Code, Codex, OpenCode, pi): per-project workspaces, worker teams, parallel runs, and access from a macOS app, Telegram/Discord/iMessage, or voice.
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI; scanned with the same pipeline.
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.
37 critical findings reported by cisco-skill-scanner, agent-audit-kit, 33 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/its-ahoh/codey, 786 findings
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI. Review the scanned source before copying them into your own project.
nerlo install -- codey-monorepo
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.
v1.4.0
2 findings · 0.6s
v2.0.11
336 findings · 23.1s
v0.3.74
8 findings · 19.1s
v0.1.0
3 findings · 23.5s
v0.1.0
36 findings · 23.5s
v0.1.0
0 findings · 27.0s
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.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 21, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | 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 385 findings across every scanner that examined this package. 4 of 37 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.
151 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, DATA_EXFIL_JS_FS_ACCESS, AAK-SECRET-004 and 2 more · Files: /repo/codey-mac/electron/browser-agent-bridge.test.ts, /repo/packages/core/src/agents/process-tree.test.ts, /repo/packages/gateway/src/chat-worktree.test.ts and 28 more · reported by cisco-skill-scanner, agent-audit-kit
41 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION, opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: docs/superpowers/specs/2026-08-07-assistant-turn-header-design.md, /repo/docs/superpowers/plans/SKILL.md, /repo/docs/superpowers/specs/SKILL.md and 9 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
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: agents-env-probing-743 · Files: CLAUDE.md · reported by agentshield
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.
113 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/codey-mac/electron/browser-agent-cli.cjs, /repo/codey-mac/electron/browser-control-permission.ts, /repo/codey-mac/electron/browser-extensions.ts and 26 more · reported by cisco-skill-scanner
29 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/codey-mac/electron/browser-webauthn.ts, /repo/packages/core/src/agents/claude-code.ts, /repo/packages/core/src/agents/codex.ts and 9 more · reported by cisco-skill-scanner
11 DATA_EXFIL_JS_NETWORK
Files: /repo/codey-mac/electron/main.ts, /repo/codey-mac/src/components/VoiceRecorder.tsx, /repo/codey-mac/src/hooks/useGitBranches.ts and 3 more · reported by cisco-skill-scanner
8 MANIFEST_MISSING_LICENSE
Files: /repo/packages/core/src/skills/browser/SKILL.md, /repo/SKILL.md, /repo/scripts/SKILL.md and 5 more · reported by cisco-skill-scanner
7 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/scripts/SKILL.md, /repo/workers/executor/SKILL.md and 4 more
The model could have called any of these a false positive and did not.
1 AAK-MCP-ENV-PLACEHOLDER-EXFIL-001
Files: codey-mac/electron/main.ts · reported by agent-audit-kit
5 The model did not answer for these findings.
Rules: agents-env-probing-693, MANIFEST_MISSING_LICENSE · Files: CLAUDE.md, /repo/docs/superpowers/plans/SKILL.md, /repo/docs/superpowers/specs/SKILL.md and 2 more · reported by agentshield, cisco-skill-scanner
Artifact allows shell execution and credential exfiltration.
The artifact contains multiple critical command injection vulnerabilities, allowing shell execution via child processes in various core and gateway components, and through `eval` in `WhisperTab.tsx` and `engine.ts`. It also has a critical finding for exfiltrating environment variable placeholders in `main.ts`. Additionally, there are high severity findings for file system access and potential secret exfiltration to the network.
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.
3 COMMAND_INJECTION_EVAL
Files: /repo/packages/gateway/src/automations/engine.ts, /repo/packages/gateway/src/channels/imessage.ts, /repo/codey-mac/src/components/WhisperTab.tsx · reported by cisco-skill-scanner
2 AAK-SECRET-004
Files: packages/core/src/types/automation.ts, codey-mac/src/components/automationsModel.ts · reported by agent-audit-kit
2 LOW_ANALYZABILITY
Files: /repo/scripts, /repo · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/codey-mac/electron/main.ts, /repo/codey-mac/src/components/VoiceRecorder.tsx · reported by nerlo-behavioral
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-SPLUNK-TOKLOG-001
Files: scripts/verify-mac-boot.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/codey-mac/build/icon.icns · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 FILE_MAGIC_MISMATCH
Files: /repo/codey-mac/index.js · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.nojekyll · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/packages/gateway/src/channels/imessage.ts · reported by nerlo-behavioral
1 UNANALYZABLE_BINARY
Files: /repo/codey-mac/build/icon.icns · reported by cisco-skill-scanner
Showing 25 of 155; the rest are in the per-scanner reports above.