Loading the registry…
Quantum keyring for AI coding tools — Cursor, Kiro, Claude Code. Secrets, superposition, entanglement, MCP.
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.
13 critical findings reported by cisco-skill-scanner, agent-audit-kit, 8 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/I4cTime/q-ring, 418 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @i4ctime/q-ring
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
29 findings · 0.7s
v2.0.11
61 findings · 12.8s
v0.3.26
39 findings · 2.6s
v0.1.0
7 findings · 28.9s
v0.1.0
0 findings · 28.9s
v0.1.0
0 findings · 24.1s
No report in this scan: capslock, 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 4, 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 136 findings across every scanner that examined this package. 5 of 13 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 16 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.
29 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-002, SECRET_GITHUB_TOKEN, AAK-SECRET-008 and 5 more · Files: src/__tests__/core/secrets-detect.test.ts, src/__tests__/core/linter.test.ts, src/__tests__/core/scan.test.ts and 6 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-behavioral
5 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, MANIFEST_MISSING_LICENSE · Files: docs/troubleshooting.md, /repo/docs/SKILL.md, /repo/.github/SKILL.md · reported by agent-audit-kit, cisco-skill-scanner
3 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, MANIFEST_INVALID_NAME · Files: .github/workflows/ci.yml, .github/workflows/publish.yml, /repo/.github/SKILL.md · reported by agent-audit-kit, 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.
19 MANIFEST_MISSING_LICENSE
Files: /repo/cursor-plugin/skills/secret-rotation/SKILL.md, /repo/cursor-plugin/skills/secret-management/SKILL.md, /repo/cursor-plugin/skills/exec-with-secrets/SKILL.md and 16 more · reported by cisco-skill-scanner
11 AAK-MCP-018
Files: src/mcp/server.ts, src/mcp/tool-registration.ts, src/mcp/tools/hooks.ts and 8 more · reported by agent-audit-kit
5 AAK-SECRET-004
Files: src/core/memory.ts, src/core/dashboard-client.ts, src/core/dashboard.ts · reported by agent-audit-kit
5 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/scripts/prepare-release.mjs, /repo/src/core/collapse.ts, /repo/src/hooks/precommit.ts and 1 more · reported by cisco-skill-scanner
4 HIDDEN_DATA_FILE
Files: /repo/.prettierrc.json, /repo/cursor-plugin/.cursor-plugin/plugin.json, /repo/.cursor-plugin/marketplace.json · reported by cisco-skill-scanner
16 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-telemetry-claude-code-plugin/commands/qring-rotate-expired.md, skills-missing-governance-claude-code-plugin/commands/qring-scan-secrets.md, skills-missing-governance-claude-code-plugin/commands/qring-analyze.md and 13 more · Files: claude-code-plugin/commands/qring-rotate-expired.md, claude-code-plugin/commands/qring-scan-secrets.md, claude-code-plugin/commands/qring-analyze.md and 5 more · reported by agentshield
Critical shell execution and credential access risks
The artifact contains multiple critical findings related to shell execution, including command injection via child processes in core utilities and `eval` in CLI commands. Remote code execution is possible through specific hook scripts. Additionally, high-severity findings indicate potential credential access or exposure within dashboard and memory management components, alongside data exfiltration capabilities in various hook scripts.
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.
4 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/cursor-plugin/SKILL.md, /repo/claude-code-plugin/SKILL.md and 1 more · reported by cisco-skill-scanner
3 AAK-MCP-006
Files: cursor-plugin/.mcp.json, claude-code-plugin/.mcp.json, kiro-plugin/mcp.json · reported by agent-audit-kit
2 AAK-HOOK-RCE-001
Files: claude-code-plugin/hooks/scripts/qring-pre-bash-env-guard.sh, claude-code-plugin/hooks/scripts/qring-post-edit-lint-hint.sh · reported by agent-audit-kit
2 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json, .cursor-plugin/marketplace.json · reported by agent-audit-kit
2 DATA_EXFIL_JS_NETWORK
Files: /repo/src/core/provision.ts, /repo/src/dashboard-client/main.js · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/src/core/dashboard-html.ts, /repo/src/core/dashboard-client.ts · reported by cisco-skill-scanner
2 hooks-no-stop-hooks
Files: claude-code-plugin/hooks/hooks.json, claude-code-plugin/.claude/settings.json · reported by agentshield
1 AAK-ANTHROPIC-SDK-001
Files: src/mcp.ts · reported by agent-audit-kit
1 AAK-HEALTHCARE-AI-004
Files: CHANGELOG.md · reported by agent-audit-kit
1 AAK-LEGAL-001
Files: package.json · reported by agent-audit-kit
1 AAK-MCP-014
Files: src/core/dashboard.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 agents-no-model-claude-code-plugin/agents/secret-ops.md
Files: claude-code-plugin/agents/secret-ops.md · reported by agentshield
1 agents-no-model-claude-code-plugin/agents/security-auditor.md
Files: claude-code-plugin/agents/security-auditor.md · reported by agentshield
1 COMMAND_INJECTION_EVAL
Files: /repo/src/cli/commands/tooling.ts · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 hooks-exfiltration-1047
Files: claude-code-plugin/hooks/scripts/qring-session-start.sh · reported by agentshield
1 hooks-exfiltration-1347
Files: claude-code-plugin/hooks/scripts/qring-post-edit-lint-hint.sh · reported by agentshield
1 hooks-exfiltration-1854
Files: claude-code-plugin/hooks/scripts/qring-pre-bash-env-guard.sh · reported by agentshield
1 hooks-logging-disabled-312
Files: claude-code-plugin/hooks/scripts/qring-session-start.sh · reported by agentshield
1 hooks-logging-disabled-425
Files: claude-code-plugin/hooks/scripts/qring-pre-bash-env-guard.sh · reported by agentshield
1 hooks-logging-disabled-429
Files: claude-code-plugin/hooks/scripts/qring-post-edit-lint-hint.sh · reported by agentshield
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/cursor-plugin/commands/SKILL.md · reported by cisco-skill-scanner
1 mcp-auto-approve-q-ring
Files: kiro-plugin/mcp.json · reported by agentshield
1 mcp-no-desc-q-ring
Files: kiro-plugin/mcp.json · reported by agentshield
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/src/dashboard-client/main.js · reported by nerlo-behavioral
1 permissions-no-block
Files: claude-code-plugin/.claude/settings.json · reported by agentshield
1 SECRET_PASSWORD_VAR
Files: /repo/src/dashboard-client/main.js · reported by cisco-skill-scanner
Showing 25 of 26; the rest are in the per-scanner reports above.