Loading the registry…
old-disabled
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.
11 critical findings reported by agent-audit-kit. 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 -- 'lin123-star/claude-for-finance (competitive-analysis)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'lin123-star/claude-for-finance (competitive-analysis)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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
44 findings · 1.3s
v2.0.11
87 findings · 19.1s
v0.3.74
23 findings · 7.7s
v0.1.0
1 finding · 5.3s
v0.1.0
0 findings · 5.3s
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 · 1.0s
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 22, 2026 | Scan Halted | — | agentshield: completecisco-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 155 findings across every scanner that examined this package. None of the 11 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 32 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
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.
33 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/financial-analysis/SKILL.md, /repo/.claude/skills/industry-research/SKILL.md, /repo/.claude/skills/dcf-model/SKILL.md and 30 more · reported by cisco-skill-scanner
28 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/outputs/SKILL.md, /repo/.claude/SKILL.md and 25 more · reported by cisco-skill-scanner
22 MANIFEST_INVALID_NAME
Files: /repo/.claude/SKILL.md, /repo/拓普集团/.claude/SKILL.md, /repo/宁德时代/.claude/SKILL.md and 19 more · reported by cisco-skill-scanner
11 AAK-MCP-001
Files: .mcp.json · reported by agent-audit-kit
11 AAK-MCP-ATTEST-001
Files: .mcp.json · reported by agent-audit-kit
3 COMMAND_INJECTION_SHELL_TRUE
Files: /repo/outputs/东山精密/东山精密_三表模型_DCF估值.py · reported by cisco-skill-scanner
1 AAK-MCP-004
Files: .mcp.json · reported by agent-audit-kit
1 agents-no-model-agents/case-library-agent.md
Files: agents/case-library-agent.md · reported by agentshield
1 agents-no-model-agents/competitor-analyst.md
Files: agents/competitor-analyst.md · reported by agentshield
1 agents-no-model-agents/dashboard-agent.md
Files: agents/dashboard-agent.md · reported by agentshield
1 agents-no-model-agents/financial-analyst.md
Files: agents/financial-analyst.md · reported by agentshield
1 agents-no-model-agents/financial-data-fetcher.md
Files: agents/financial-data-fetcher.md · reported by agentshield
1 agents-no-model-agents/macro-researcher.md
Files: agents/macro-researcher.md · reported by agentshield
1 agents-no-model-agents/master-orchestrator.md
Files: agents/master-orchestrator.md · reported by agentshield
1 agents-no-model-agents/monitor-agent.md
Files: agents/monitor-agent.md · reported by agentshield
1 agents-no-model-agents/quality-checker.md
Files: agents/quality-checker.md · reported by agentshield
1 agents-no-model-agents/research-report-summarizer.md
Files: agents/research-report-summarizer.md · reported by agentshield
1 agents-no-model-agents/signal-integrator.md
Files: agents/signal-integrator.md · reported by agentshield
1 agents-no-model-agents/valuation-expert.md
Files: agents/valuation-expert.md · reported by agentshield
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/outputs/东山精密/东山精密_三表模型_DCF估值.py · reported by nerlo-behavioral
32 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-commands/manufacturing-analysis.md, skills-missing-telemetry-commands/case-list.md, skills-missing-governance-commands/analyze-company.md and 29 more · Files: commands/manufacturing-analysis.md, commands/case-list.md, commands/analyze-company.md and 13 more · reported by agentshield
Critical policy violations and shell execution risks identified.
The artifact contains critical policy violations within its configuration files. Additionally, it exhibits capabilities for shell command injection and dynamic code execution in the file `/repo/outputs/东山精密/东山精密_三表模型_DCF估值.py`. These findings indicate potential for unauthorized system access or arbitrary code execution.
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.