Back to skill
Skillv1.0.0
ClawScan security
Adaptive Reasoning · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 30, 2026, 8:00 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions, required resources, and actions are consistent with its stated purpose of adaptively enabling extended reasoning; it asks for no credentials, installs, or filesystem access.
- Guidance
- This skill is coherent and lightweight: it only provides runtime instructions for when to enable extended reasoning and does not access files, credentials, or install code. Consider whether you want the agent to autonomously toggle 'reasoning mode' (it may produce longer answers and higher token usage) and whether you prefer the agent to ask the user before enabling extended thinking. If you want tighter control, keep the skill user-invocable and/or disable automatic activation in your agent settings.
Review Dimensions
- Purpose & Capability
- okName/description match the SKILL.md: it scores requests and toggles reasoning mode. The skill declares no external dependencies, credentials, or installs—appropriate for an instruction-only preprocessing helper.
- Instruction Scope
- noteThe SKILL.md tells the agent to silently enable/disable an internal reasoning mode (/reasoning on, session_status tool) and to append visual icons. This is within the skill's stated purpose, but it grants the agent autonomous control over its reasoning state and response length/token usage (no data exfiltration or unrelated file/env access is instructed).
- Install Mechanism
- okNo install spec or code files are present (instruction-only). Nothing will be downloaded or written to disk as part of installation.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths—proportionate to its function.
- Persistence & Privilege
- okalways is false and the skill doesn't request persistent system-wide privileges or modify other skills' configs. It instructs the agent to toggle its internal reasoning state but does not request elevated access.