Back to skill
Skillv1.0.1
ClawScan security
Semver Helper · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 18, 2026, 9:42 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only semantic versioning reference; its content, required permissions, and runtime instructions are consistent with its stated purpose.
- Guidance
- This skill is a simple, read-only SemVer reference with no installs, no credentials, and no external calls — safe to add. Note that the agent may call the skill autonomously (platform default), but the skill itself has no ability to access secrets or modify system state.
Review Dimensions
- Purpose & Capability
- okThe name and description match the SKILL.md content (a SemVer 2.0.0 reference). The skill requests no binaries, env vars, or config paths — everything requested is proportional to a read-only reference guide.
- Instruction Scope
- okSKILL.md contains only static guidance, decision trees, and examples. It does not instruct the agent to read files, access environment variables, execute commands, or send data to external endpoints.
- Install Mechanism
- okNo install specification and no code files are present (instruction-only). Nothing will be written to disk or downloaded during install.
- Credentials
- okNo environment variables, credentials, or config paths are required. There are no secrets requested or implied by the instructions.
- Persistence & Privilege
- okThe skill does not request always:true and makes no changes to other skills or system config. It is user-invocable and may be invoked autonomously (platform default), which is appropriate for a harmless helper.