Loading the registry…
Run Python functions and notebook cells on the cheapest suitable remote GPU — per-task billing, no instances
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.
377 critical findings reported by cisco-skill-scanner, agent-audit-kit, 15 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/Ilya-a-sergeyev-ger/krauncher, 437 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- krauncher
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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.
v2.0.11
29 findings · 8.1s
v0.3.26
406 findings · 3.6s
v0.1.0
0 findings · 27.9s
v0.1.0
0 findings · 27.9s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
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, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 10, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | 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 435 findings across every scanner that examined this package. 362 of 377 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.
359 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, AAK-AGENT-002, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner
11 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-TASKS-003 · Files: /repo/tests/test_codeblock.py, /repo/tests/test_namespace.py, /repo/tests/test_serializer.py and 5 more · 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.
38 AAK-TASKS-003
Files: krauncher/relay_pb2_grpc.py, krauncher/exceptions.py, krauncher/KrauncherClient.py and 35 more · reported by agent-audit-kit
14 COMMAND_INJECTION_EVAL
Files: /repo/tutorial/19_huggingface_dataset.py, /repo/tutorial/22_qwen25_7b_inference_gsm8k.py, /repo/tutorial/23_gnn_node_classification_cora.py and 11 more · reported by cisco-skill-scanner
4 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/krauncher/analyzer.py, /repo/krauncher/models.py, /repo/tutorial/04_timeout.py · reported by cisco-skill-scanner
2 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/mcp/SKILL.md · reported by cisco-skill-scanner
2 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/mcp/SKILL.md · reported by cisco-skill-scanner
1 AAK-SECRET-003
Critical command injection and credential exposure
The artifact contains multiple instances of command injection vulnerabilities, particularly in `krauncher/codeblock.py`, `krauncher/serializer.py`, and several tutorial files, which could lead to arbitrary shell execution. A critical finding indicates potential credential exposure in `.env.example`. Additionally, high severity findings point to potential resource abuse through infinite loops in `krauncher/analyzer.py` and `krauncher/models.py`, and further credential exposure in `.env.example`.
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: .env.example · reported by agent-audit-kit
1 AAK-SECRET-004
Files: .env.example · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-TASKS-001
Files: krauncher/KrauncherClient.py · reported by agent-audit-kit
1 AAK-TASKS-002
Files: krauncher/KrauncherClient.py · reported by agent-audit-kit