Loading the registry…
Install cubic AI code review skills and MCP configuration for AI coding tools
Claude Skills are markdown + scripts loaded into Claude Code; 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.
61 critical findings reported by cisco-skill-scanner, agent-audit-kit, 2 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/mrge-io/skills, 134 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- @cubic-plugin/cubic-plugin
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- @cubic-plugin/cubic-plugin ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
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
12 findings · 0.7s
v2.0.11
113 findings · 6.5s
v0.3.74
6 findings · 1.1s
v0.2.0
0 findings · 3.3s
v0.2.0
3 findings · 3.3s
v0.1.0
0 findings · 8.7s
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.
4 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 18, 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 2, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 26, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-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 134 findings across every scanner that examined this package. 59 of 61 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 10 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.
60 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_EVAL, AAK-OAUTH-005 · Files: /repo/test/cli.test.mjs, test/cli.test.mjs · reported by cisco-skill-scanner, agent-audit-kit
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.
34 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/src/targets/codex.ts, /repo/src/targets/cursor.ts, /repo/src/targets/droid.ts and 8 more · reported by cisco-skill-scanner
8 MANIFEST_MISSING_LICENSE
Files: /repo/skills/cubic-loop/SKILL.md, /repo/skills/check-pr-comments/SKILL.md, /repo/skills/run-review/SKILL.md and 5 more · reported by cisco-skill-scanner
7 PIPELINE_TAINT_FLOW
Files: /repo/commands/run-review.md, /repo/skills/cubic-loop/SKILL.md, /repo/skills/run-review/SKILL.md and 1 more · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/commands/run-review.md, /repo/skills/cubic-loop/SKILL.md, /repo/skills/run-review/SKILL.md · reported by nerlo-install-instruction
2 AAK-MARKETPLACE-001
Files: .cursor-plugin/marketplace.json, .claude-plugin/marketplace.json · reported by agent-audit-kit
10 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-commands/run-review.md, skills-missing-telemetry-commands/learnings.md, skills-missing-telemetry-commands/run-review.md and 7 more · Files: commands/run-review.md, commands/learnings.md, commands/comments.md and 2 more · reported by agentshield
Critical command injection and data exfiltration risks identified.
The artifact includes critical command injection capabilities in `/repo/src/utils.ts`, allowing for shell execution. Multiple high-severity findings indicate file system access in various scripts and target files, such as `/repo/scripts/clean-home-install.mjs` and `/repo/src/targets/codex.ts`, which could lead to data exfiltration. Additionally, a critical issue related to `mcp.json` and high-severity pipeline taint flow findings in `/repo/commands/run-review.md` warrant attention.
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.
2 HIDDEN_DATA_FILE
Files: /repo/.cursor-plugin/plugin.json, /repo/.cursor-plugin/marketplace.json · reported by cisco-skill-scanner
1 AAK-MCP-001
Files: mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: mcp.json · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/src/utils.ts · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 mcp-no-desc-cubic
Files: mcp.json · reported by agentshield
1 mcp-url-transport-cubic
Files: mcp.json · reported by agentshield
1 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md · reported by cisco-skill-scanner
Showing 25 of 45; the rest are in the per-scanner reports above.