llm-models

Pass

Audited by Runlayer on Mar 15, 2026

Risk Level: LOW
Scan Summary
Max Score
74%
Files
1
Flagged
1
Chunks
1
Flagged Files (1)
llm-models/SKILL.mdLOW
74.4%

Risky tool definition detected

### Claude Haiku (Fast & Cheap) ```bash infsh app run openrouter/claude-haiku-45 --input '{ "prompt": "Translate this to French: Hello, how are you?" }' ``` ### Kimi K2 (Thinking Agent) ```bash infsh app run openrouter/kimi-k2-thinking --input '{ "prompt": "Plan a step-by-step approach to build a web scraper" }' ``` ### Any Model (Auto-Select) ```bash # Automatically picks the most cost-effective model infsh app run openrouter/any-model --input '{ "prompt": "What is the capital of France?" }' ``

Audit Metadata
Max File Score
74%
Classification
KNOWN_SERVER_KNOWN_TOOL_LIST
Files Scanned
1
Files Flagged
1
Chunks Analyzed
1
Analyzed
Mar 15, 2026, 05:17 PM
Security Audit — runlayer — llm-models