Back to skill
Skillv0.1.0
ClawScan security
Ouwibo: general · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 16, 2026, 6:24 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a minimal, instruction-only general-assistant skill whose requests and instructions are consistent with its stated purpose.
- Guidance
- This skill is a lightweight template for assistant behavior and appears coherent. Before installing, consider: (1) Confirm what 'search' means on your platform (which search provider/API will be used) and whether search queries may be sent to external services you don't control. (2) If you have privacy or compliance concerns, restrict or configure web-search capability on the agent. (3) Watch for future/other skills that add environment variables or install steps — those change the risk profile.
Review Dimensions
- Purpose & Capability
- okName/description match the SKILL.md directives. The skill requests no env vars, binaries, or installs — all proportional to a generic assistant template.
- Instruction Scope
- noteInstructions are narrowly scoped to general assistant behavior (best-effort answers, prefer searching for 'latest' queries, concise formatting). They do ask the agent to 'prefer searching first' for current info but do not specify what search mechanism or external endpoint to use; no file, path, or credential access is requested.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill, so nothing is written to disk or fetched during install.
- Credentials
- okRequires no environment variables, credentials, or config paths; no unexpected secrets are requested.
- Persistence & Privilege
- okDoes not request always:true or other elevated persistence. Default autonomous invocation is allowed (platform default) and appropriate for this kind of skill.