Loading the registry…
OceanBase Diagnostic Tool - cluster diagnosis, log gathering and analysis
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.
24 critical findings reported by cisco-skill-scanner, agent-audit-kit, 23 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- obdiag
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- obdiag ~/.claude/skills/
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
76 findings · 21.2s
v0.3.74
131 findings · 52.7s
v0.1.0
9 findings · 16.0s
v0.1.0
1 finding · 16.0s
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
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.8s
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 217 findings across every scanner that examined this package. None of the 24 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 64 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.
9 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/translate.yml, .github/workflows/build_obdiag_docker.yml, .github/workflows/build_base_docker.yml · reported by agent-audit-kit
2 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-IPI-WILD-CORPUS-001 · Files: test/common/test_sql_table_extractor.py, test/analyzer/sql/test_update_delete_multi_table_rule.py · reported by agent-audit-kit
The model could have called any of these a false positive and did not.
107 AAK-TASKS-003
Files: plugins/check/tasks/observer/tenant/writing_throttling_trigger_percentage.py, plugins/check/tasks/observer/tenant/ddl_operation_table_size.py, plugins/check/tasks/observer/tenant/tenant_min_resource.py and 104 more · reported by agent-audit-kit
14 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/rca/oms_obcdc.py, /repo/src/common/ocp/ocp_task.py, /repo/src/common/tool.py and 5 more · reported by cisco-skill-scanner
3 FILE_MAGIC_MISMATCH
Files: /repo/plugins/display/tasks/observer/memory.yaml, /repo/plugins/gather/tasks/observer/memory.yaml, /repo/plugins/display/tasks/observer/server_info.yaml · reported by cisco-skill-scanner
3 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/src/handler/agent/tui/main.py · reported by cisco-skill-scanner
3 YARA_autonomy_abuse_generic
Files: /repo/src/handler/agent/tui/config.py · reported by cisco-skill-scanner
2 RESOURCE_ABUSE_INFINITE_LOOP
40 The model's answer could not be read.
Rules: YARA_command_injection_generic, YARA_sql_injection_generic, PATH_TRAVERSAL_OPEN and 6 more · Files: /repo/dockerfiles/Dockerfile.builder-centos7, /repo/dockerfiles/Dockerfile.dev, /repo/src/handler/analyzer/analyze_parameter.py and 19 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-behavioral
24 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: TOOL_ABUSE_UNDECLARED_NETWORK, AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION and 3 more · Files: /repo/repo/LEGAL.md, README.md, /repo/SKILL.md and 19 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-install-instruction
Critical vulnerabilities found, including shell execution and injection risks.
The artifact contains critical findings related to shell execution, command injection, and SQL injection, indicating potential for arbitrary code execution and data manipulation. Path traversal vulnerabilities are also present, which could allow access to restricted files. Additionally, the artifact exhibits DNS rebinding and resource abuse capabilities, warranting immediate attention.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Showing 1 of 1; the rest are in the per-scanner reports above.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
Files: /repo/src/handler/agent/tui/skills/skill_crypto.py, /repo/src/handler/agent/tui/textual_adapter.py · reported by cisco-skill-scanner
1 AAK-IPI-WILD-CORPUS-001
Files: src/handler/meta/ob_error.py · reported by agent-audit-kit
1 AAK-MCP-LANGGRAPH-CHECKPOINT-CVE-2026-71433-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-MCP-NOAUTH-DEFAULT
Files: src/handler/agent/models.py · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-SSRF-TOCTOU-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 COMMAND_INJECTION_SHELL_TRUE
Files: /repo/src/common/ssh_client/local_client.py · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 FIND_EXEC_PATTERN
Files: /repo/rpm/init.sh · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/src/handler/agent/toolsets/knowledge_base.py · reported by nerlo-behavioral