Loading the registry…
A model context protocol for the ViperGPT visual question-answering framework.
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.
44 critical findings reported by cisco-skill-scanner, agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- viper
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
56 findings · 20.9s
v0.3.74
27 findings · 32.0s
v0.1.0
2 findings · 10.7s
v0.1.0
0 findings · 10.7s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 2.3s
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 20, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·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 85 findings across every scanner that examined this package. None of the 44 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 7 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.
1 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: DATA_EXFIL_NETWORK_REQUESTS · Files: /repo/tests/test_api.py · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
42 COMMAND_INJECTION_EVAL
Files: /repo/viper/src/base_models/maskrcnn_benchmark/engine/evolution.py, /repo/viper/src/base_models/maskrcnn_benchmark/engine/inference.py, /repo/viper/src/base_models/maskrcnn_benchmark/engine/predictor.py and 18 more · reported by cisco-skill-scanner
16 AAK-SECRET-004
Files: viper/src/base_models/maskrcnn_benchmark/engine/inference.py, viper/src/base_models/maskrcnn_benchmark/engine/predictor_glip.py, viper/src/base_models/maskrcnn_benchmark/engine/predictor_glip_v2.py and 3 more · reported by agent-audit-kit
3 AAK-MCP-HTTP-NOAUTH-SERVER-001
Files: run_server.py, Dockerfile, viper/mcp/server.py · reported by agent-audit-kit
2 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/viper/mcp/server.py, /repo/viper/src/base_models/maskrcnn_benchmark/engine/inference.py · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/viper/src/base_models/maskrcnn_benchmark/modeling/rpn/dyhead.py, /repo/viper/src/base_models/maskrcnn_benchmark/modeling/rpn/vldyhead.py · reported by nerlo-behavioral
2 RESOURCE_ABUSE_INFINITE_LOOP
4 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-SECRET-002, TOOL_ABUSE_UNDECLARED_NETWORK, MANIFEST_MISSING_LICENSE · Files: smithery.yaml, /repo/repo/README.md, /repo/SKILL.md and 1 more · reported by agent-audit-kit, cisco-skill-scanner
3 The model did not answer for these findings.
Rules: AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION · Files: viper/src/useful_lists/random_negatives.txt, /repo/SKILL.md, /repo/viper/src/base_models/maskrcnn_benchmark/utils/SKILL.md · reported by agent-audit-kit, cisco-skill-scanner
Artifact enables shell execution, file system access, and exposes credentials.
The artifact contains multiple critical command injection vulnerabilities, allowing shell execution in various engine and modeling files. It also has a critical path traversal vulnerability, enabling arbitrary file system access in a data evaluation component. Additionally, a critical secret exposure is present in `smithery.yaml`, and other critical findings from the 'bearer' scanner are noted across several core files. High severity findings also indicate dynamic code execution and potential network egress.
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.
1 AAK-DNS-REBIND-002
Files: requirements.txt · reported by agent-audit-kit
1 AAK-MCP-018
Files: viper/mcp/server.py · reported by agent-audit-kit
1 AAK-MCP-SDK-CVE-2026-52869-001
Files: requirements.txt · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: requirements.txt · reported by agent-audit-kit
1 AAK-SSRF-002
Files: viper/mcp/server.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 ARCHIVE_FILE_DETECTED
Files: /repo/viper/src/base_models/maskrcnn_benchmark/modeling/language_backbone/bpe_simple_vocab_16e6.txt.gz · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 PATH_TRAVERSAL_OPEN
Files: /repo/viper/src/base_models/maskrcnn_benchmark/data/datasets/evaluation/vg/vg_eval.py · reported by cisco-skill-scanner
1 UNANALYZABLE_BINARY
Files: /repo/viper/src/base_models/maskrcnn_benchmark/modeling/language_backbone/bpe_simple_vocab_16e6.txt.gz · reported by cisco-skill-scanner
Showing 21 of 21; the rest are in the per-scanner reports above.