v1.0.0

AI模型切换器

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:28 AM.

Analysis

This appears to be a purpose-aligned model-switching helper, but users should notice that cloud modes can route future prompts or documents to third-party models and that the skill keeps local usage logs.

GuidanceBefore installing, decide whether you want a skill that helps switch between local and cloud models. Use local mode for sensitive data, check cloud model costs and provider policies, and periodically review the local switch logs and stats files if usage history matters to you.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityLowConfidenceHighStatusNote

scripts/ai-model-switcher.txt

Write-Host "  openclaw config set model `"$($model.id)`"" ... Write-Host "📝 请手动执行以上命令完成切换"

The skill's main action is to change the OpenClaw model setting, which can affect future agent behavior, cost, and provider routing. The visible script makes this a manual user step.

User impactIf the user runs the generated command, later OpenClaw work may use a different local or cloud model.

RecommendationOnly execute the generated model-change command when you intend to change the active model, and verify the selected model and cost first.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

SKILL.md

长文档处理 | `longdoc` | Kimi云模型 ... 编程开发 | `code` | DeepSeek云模型

Several task modes intentionally select cloud models instead of the local Ollama model, which changes where future prompts, code, or documents may be processed.

User impactSensitive prompts, documents, or code may be handled by cloud model providers when cloud modes are selected.

RecommendationUse the local model for sensitive work unless you are comfortable with the relevant cloud provider handling the data.

Memory and Context Poisoning

SeverityInfoConfidenceHighStatusNote

scripts/ai-model-switcher.txt

$logFile = Join-Path $configDir "switch.log"; $statsFile = Join-Path $configDir "stats.json" ... Add-Content $logFile

The skill persists switch history and usage statistics locally. The visible code records model/task metadata and token/cost counters, not prompt contents.

User impactLocal files may reveal which models and task modes were used over time.

RecommendationReview or delete the local switch log and stats file if you do not want this usage history retained.