Skillv1.0.0

ClawScan security

Legal Discovery Request Planner · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 26, 2026, 1:09 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is a document-only, descriptive skill whose requested resources and runtime instructions match its stated purpose and contain no code, credentials, or install steps.
Guidance: This skill appears coherent and low-risk because it is documentation-only and declares no network or code execution. Before installing: (1) remember it is informational only — verify outputs with qualified counsel and local rules; (2) avoid pasting confidential or privileged client data into the chat (the skill does not request credentials but any user-provided case facts could be sensitive); and (3) if you later modify this package to add handlers or scripts, re-evaluate for network calls, credentials, or unexpected install behavior.

Purpose & Capability: okName, description, and files are all descriptive-only and focused on legal discovery planning. There are no declared env vars, binaries, or install steps that would be unrelated to the stated purpose.
Instruction Scope: okSKILL.md contains only guidance, templates, checklists, inputs to collect, and explicit legal/ethical limitations. It does not instruct the agent to read files, call external APIs, execute commands, or access system configuration.
Install Mechanism: okNo install spec and no code files — the package is instruction-only. ACCEPTANCE.md enforces that no handler/scripts/executables are present, so there is nothing written to disk or fetched at install time.
Credentials: okNo environment variables, credentials, or config paths are requested. The skill does not need any external secrets or cloud access to perform its described functions.
Persistence & Privilege: okalways is false and there is no install or runtime component that would request persistent privileges or modify other skills or system-wide settings.