Back to skill
Skillv1.0.0
ClawScan security
Scannable Reports · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 27, 2026, 8:01 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only formatting guide for chat-friendly text output and requests no credentials, installs, or system access — its declared purpose matches its content.
- Guidance
- This skill appears low-risk: it only provides text-formatting guidance for chat apps and does not install code or request secrets. Things to consider before installing: (1) provenance is unknown (no homepage/author page) — if you require third-party provenance, seek an authored source; (2) emoji/monospace rendering varies by platform and device, so test examples on your target apps; (3) autonomous invocation is allowed by default on the platform (normal), so if you want to restrict the agent from auto-applying formatting, disable or limit skill invocation in your agent policies.
Review Dimensions
- Purpose & Capability
- okName and description (mobile chat formatting: progress bars, sparklines, status indicators) align with the SKILL.md content. The skill does not ask for unrelated permissions or resources.
- Instruction Scope
- okSKILL.md contains only formatting rules, examples, and platform notes. It does not instruct the agent to read files, access environment variables, call external endpoints, or perform actions outside producing formatted text.
- Install Mechanism
- okNo install spec and no code files — nothing is downloaded or written to disk. This is the lowest-risk model (instruction-only).
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. There are no suspicious or excessive secret requests.
- Persistence & Privilege
- okFlags are default (not always:true). The skill does not request permanent presence or attempt to modify other skills or system config.