Back to skill
Skillv1.0.1
ClawScan security
skill-creator · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 5, 2026, 5:09 PM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's files, runtime instructions, and included scripts are coherent with its stated purpose as a skill-creation guide and contain no disproportionate or unrelated requirements.
- Guidance
- This package appears to be a legitimate skill-authoring template with helper scripts. Before running any of the provided scripts (init_skill.py, package_skill.py, quick_validate.py), inspect them and run them only on directories you control — they create and write files and will package whatever you point them at. Note the files do not perform network calls or require credentials, and the repo is Apache-2.0 licensed. If you want extra caution, run the scripts in a sandbox or ephemeral VM. If you see later versions that add network endpoints, requests for tokens/keys, or write outside user-specified paths, treat those as suspicious and re-evaluate.
Review Dimensions
- Purpose & Capability
- okName and description ('skill-creator' guide) align with what is included: SKILL.md guidance plus helper scripts to initialize, validate, and package skills. The bundled scripts (init_skill.py, package_skill.py, quick_validate.py) are directly relevant to authoring and packaging skills.
- Instruction Scope
- okSKILL.md contains guidance about skill structure, frontmatter, references, and workflows only; it does not instruct reading unrelated system files or exfiltrating data. The scripts operate on user-supplied paths and SKILL.md files (expected for an initializer/packager/validator).
- Install Mechanism
- okNo install spec is provided (instruction-only). There are no downloads, third-party installers, or extract steps. This minimizes install-time risk.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The scripts read and write local filesystem paths supplied by the user, which is reasonable for tooling that creates/validates/packages skill folders.
- Persistence & Privilege
- okalways:false (default) and disable-model-invocation:false. The skill does not request permanent presence or modify other skills' configurations. The scripts create files only in target directories given by the user and do not alter system-wide settings.