Skillv0.3.1

ClawScan security

Swift Architecture Skill · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignFeb 17, 2026, 8:27 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This instruction-only skill is internally consistent with its stated purpose: it provides Swift architecture playbooks and guidance and asks for no credentials, installs, or unexpected capabilities.
Guidance: This skill appears coherent and safe in that it only contains guidance documents and an instruction workflow. Before using it, decide what code/PRs you want the agent to inspect (the skill expects to analyze existing code when requested) and avoid exposing unrelated secrets or full repository access unnecessarily. Also review any generated code or step-by-step migration instructions before applying them — the skill provides patterns and checklists, not a sandboxed compile/run step.

Purpose & Capability: okThe name/description (Swift architecture guidance) matches the included reference files and runtime instructions. There are no unrelated environment variables, binaries, or config paths requested.
Instruction Scope: noteSKILL.md directs the agent to analyze request context and existing code when applicable, produce file/module layouts, and adapt reference checklists. This is appropriate for an architecture helper, but it implies the agent will need access to user-provided code/PR diffs to do line-level reviews — ensure you only provide the repository/PR content you intend the skill to read.
Install Mechanism: okNo install spec and no code files with executable install steps — the skill is instruction-only and does not write to disk or download third-party artifacts.
Credentials: okThe skill requests no environment variables, credentials, or config paths. Nothing disproportionate to the stated purpose is asked for.
Persistence & Privilege: okalways is false and there is no mechanism to persist or escalate privileges. The skill does not modify other skills or system-wide settings.