Back to skill
Skillv1.0.0
ClawScan security
Legal Trial Preparation Checklist · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 26, 2026, 2:16 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a descriptive, instruction-only checklist skill that does not request credentials, install code, or perform network activity and is consistent with its stated purpose.
- Guidance
- This skill is document-only and coherent with its stated purpose. It does not run code or access external services, but it also does not provide legal advice — verify all outputs and jurisdiction-specific rules with qualified counsel. Avoid pasting sensitive or privileged client data into any third-party skill prompt; treat outputs as planning aids only and perform attorney review before relying on them in a case.
Review Dimensions
- Purpose & Capability
- okThe skill's name, description, SKILL.md, README, and skill.json are all aligned: it provides checklists/templates for trial preparation and does not declare any unrelated dependencies or credentials.
- Instruction Scope
- okSKILL.md contains only guidance for collecting user-provided context and producing checklists/templates. It does not instruct the agent to read local files, call external APIs, execute commands, or access system state beyond user inputs.
- Install Mechanism
- okNo install spec or code files are present; the package is instruction-only so nothing is written to disk or downloaded during install.
- Credentials
- okThe package does not request environment variables, credentials, or config paths. Inputs it asks for (case context, documents, jurisdiction) are appropriate for a checklist generator.
- Persistence & Privilege
- okalways is false and there are no indications the skill attempts to modify agent/system settings or persist data. The skill can be invoked by the agent per default behavior, which is normal for descriptive skills.