Back to skill
Skillv1.0.1
ClawScan security
clarify-me · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 13, 2026, 3:34 PM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's requested actions, scope, and lack of installs/credentials align with its stated purpose of analyzing recent conversation turns and suggesting clearer questions.
- Guidance
- This is a low-risk, instruction-only skill that simply reads recent conversation turns to point out vague phrases and suggest clearer questions. Before installing, note that the skill needs access to the chat history (the last few exchanges) to work — avoid invoking it on conversations that include sensitive secrets. Because it has no installs or credentials, its footprint is minimal. If you want extra caution, keep it user-invocable only (don't change platform settings to make it always run) and review the SKILL.md contents (already shown) to confirm its behavior matches your expectations.
Review Dimensions
- Purpose & Capability
- okName/description ask for conversational clarification and the SKILL.md only requires reading recent conversation history and producing suggestions — nothing requested is outside that purpose.
- Instruction Scope
- okRuntime instructions instruct the agent to read the last few exchanges, identify vague wording and missing context, and produce friendly suggestions in the user's language — these stay within the skill's stated scope and do not request unrelated data or external transmission.
- Install Mechanism
- okNo install spec or code files are provided (instruction-only). No downloads, package installs, or filesystem writes are required.
- Credentials
- okThe skill declares no environment variables, credentials, or config paths. That is proportionate for a clarification/analysis-only skill.
- Persistence & Privilege
- okalways is false and the skill is user-invocable. It does not request persistent system presence or modify other skills. The default ability for the agent to invoke the skill autonomously is unchanged but not elevated by the skill.