Back to skill
Skillv1.0.0
ClawScan security
Mermaid Architect · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 12, 2026, 11:33 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only Mermaid diagram helper that requests no credentials, installs nothing, and its requirements match its stated purpose, though it references example files/scripts that aren't bundled.
- Guidance
- This skill is coherent and low-risk: it only contains Mermaid syntax rules and examples and asks for nothing sensitive. Before installing or using it, note that SKILL.md references a validator script and example assets that are not bundled — if you expect those to run, request the missing scripts/assets or provide your own validator. As usual, review any generated Mermaid text before rendering in a web context and avoid pasting sensitive data into diagrams.
Review Dimensions
- Purpose & Capability
- okName/description (Mermaid diagram generation) align with the provided instructions and reference material: the files only contain Mermaid syntax guidance and diagram-generation rules. There are no unrelated environment variables, binaries, or network endpoints requested.
- Instruction Scope
- noteThe SKILL.md stays within diagram-generation scope (rules for node IDs, quoted labels, layout, and examples). It does reference running a local validator ('scripts/validate-mmd') and several example asset paths ('assets/examples/*.mmd' and assets/examples/* .mmd) that are not included in the manifest; this is an inconsistency (missing helper script/assets) but not an obvious security issue. The instructions do not direct the agent to read user secrets, system config, or external endpoints.
- Install Mechanism
- okNo install spec or code is provided (instruction-only), so nothing is downloaded or written to disk by the skill itself — lowest-risk install profile.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The instructions do not reference any hidden env vars or external credentials.
- Persistence & Privilege
- okThe skill does not request always:true and uses default invocation settings. Autonomous invocation is allowed (platform default) but there is no indication this skill needs persistent privileges or system-wide configuration changes.