Loading the registry…
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
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.
50 critical findings reported by cisco-skill-scanner, agent-audit-kit, 16 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/cerebrixos-org/tuning-engines-cli, 156 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- tuningengines-cli
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
1 finding · 1.7s
v2.0.11
97 findings · 19.5s
v0.3.26
54 findings · 7.6s
v0.1.0
4 findings · 37.4s
v0.1.0
0 findings · 37.4s
v0.1.0
0 findings · 23.1s
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 2, 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 156 findings across every scanner that examined this package. 34 of 50 findings rated critical by their scanner were among the dismissals.
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.
32 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-001, secrets-claude-md-env-304, TOOL_ABUSE_UNDECLARED_NETWORK · Files: CLAUDE.md, /repo/repo/CLAUDE.md · reported by agent-audit-kit, agentshield, cisco-skill-scanner
20 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-MCP-015, COMMAND_INJECTION_JS_CHILD_PROCESS, AAK-ANTHROPIC-SDK-001 and 2 more · Files: test_guard_claude_install.mjs, test_guard_runtime_adapters.mjs, /repo/test_guard_claude_install.mjs and 4 more · reported by agent-audit-kit, cisco-skill-scanner
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/SKILL.md · reported by cisco-skill-scanner
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: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/publish-pypi.yml · reported by 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.
44 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/dist/commands/files.js, /repo/dist/commands/guard.js, /repo/dist/commands/orchestration.js and 15 more · reported by cisco-skill-scanner
14 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/dist/commands/guard.js, /repo/scripts/smoke/inference-smoke.mjs, /repo/src/commands/guard.ts and 4 more · reported by cisco-skill-scanner
6 AAK-MCP-007
Files: .mcp.json, plugins/tuning-engines/.mcp.json · reported by agent-audit-kit
6 DATA_EXFIL_JS_NETWORK
Files: /repo/dist/commands/orchestration.js, /repo/dist/inference_request.js, /repo/scripts/smoke/inference-smoke.mjs and 2 more · reported by cisco-skill-scanner
4 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/packages/tuning-agents/SKILL.md, /repo/scripts/smoke/SKILL.md and 1 more · reported by cisco-skill-scanner
Artifact contains critical command injection and dynamic execution vulnerabilities.
The artifact exhibits critical command injection vulnerabilities via `child_process` and `eval` in multiple command files, including `auth.js`, `billing.js`, and `guard.js`, enabling shell execution. It also performs dynamic code execution in `src/commands/auth.ts`. Furthermore, the artifact handles secrets that can lead to network egress in `scripts/smoke/inference-smoke.mjs` and contains potential credential logging in the same file.
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.
Files: /repo/SKILL.md, /repo/packages/tuning-agents/SKILL.md, /repo/scripts/smoke/SKILL.md and 1 more · reported by cisco-skill-scanner
3 AAK-SUPPLY-001
Files: .mcp.json · reported by agent-audit-kit
2 AAK-MCP-005
Files: .mcp.json, plugins/tuning-engines/.mcp.json · reported by agent-audit-kit
2 AAK-TASKS-003
Files: src/commands/guard.ts, src/commands/orchestration.ts · reported by agent-audit-kit
2 COMMAND_INJECTION_EVAL
Files: /repo/src/commands/auth.ts, /repo/src/commands/billing.ts · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/scripts/smoke, /repo · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/src/commands/auth.ts, /repo/src/commands/billing.ts · reported by nerlo-behavioral
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/scripts/smoke/inference-smoke.mjs, /repo/src/inference_request.ts · reported by nerlo-behavioral
1 AAK-ANTHROPIC-SDK-001
Files: src/mcp.ts · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-SECRET-004
Files: src/adapters/shared.ts · reported by agent-audit-kit
1 AAK-SPLUNK-TOKLOG-001
Files: scripts/smoke/inference-smoke.mjs · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/packages/tuning-agents/repo/packages/tuning-agents/README.md · reported by cisco-skill-scanner
Showing 25 of 27; the rest are in the per-scanner reports above.