Skillv1.0.0

ClawScan security

多模型路由器 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 28, 2026, 6:55 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This instruction-only skill is internally consistent: it describes a model-routing strategy and does not request unrelated credentials, installs, or system access.
Guidance: This skill is a coherent design doc for routing tasks to different LLMs and is safe as-is (no installs or credential requests). Before using it in a live agent, ensure the concrete integration: (1) only supplies API keys for provider(s) you trust and scope those keys appropriately, (2) audits any code that implements call_model/test_quality to avoid sending sensitive data to external models, (3) considers cost impact of parallel calls or testing fallbacks, and (4) adds logging, rate limiting, and privacy controls. If you want a security review of an implementation (code that actually calls model APIs), provide that code or the integration plan so it can be evaluated for credential handling and network behavior.

Purpose & Capability: okThe name/description (multi-model router to pick models by task characteristics) matches the content of SKILL.md: routing logic, model strengths, cost-optimization and switching strategies. The declared requirements (none) are proportionate to the provided instructions, which are high-level and platform-agnostic.
Instruction Scope: okAll runtime instructions are pseudocode and prose about task classification, routing, and monitoring. They do not tell the agent to read unrelated files, access environment variables, or exfiltrate data. The instructions are high-level and will require concrete integration code to actually call model APIs.
Install Mechanism: okNo install specification or code files are present; this is lowest-risk (instruction-only). Nothing will be written to disk by the skill as provided.
Credentials: noteThe skill itself does not request any environment variables or credentials, which is appropriate for the documentation-level content. However, implementing the routing (call_model, test_quality, etc.) in a real system will require API keys/credentials for whichever model providers are used; those should be requested only at integration time and scoped narrowly.
Persistence & Privilege: okSkill does not request always:true and makes no claims about modifying other skills or system settings. Autonomous invocation is allowed by platform default but the skill's content does not demand elevated persistence.