Back to skill
Skillv1.0.0
ClawScan security
Obsidian Markdown · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 4, 2026, 6:42 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only skill that documents Obsidian-flavored Markdown syntax; it requests no credentials, installs nothing, and its runtime instructions stay within the stated purpose.
- Guidance
- This skill is a documentation/formatting helper for Obsidian Markdown and appears internally consistent and low-risk: it doesn't install software, request credentials, or instruct the agent to access files or networks. If you plan to let agents act autonomously, note the skill can be invoked by the agent as normal — but this skill's content is read-only guidance. If you need guarantees, verify the skill source or only enable it for users who need markdown-authoring assistance.
Review Dimensions
- Purpose & Capability
- okName/description match the contents: the files provide guidance on Obsidian-specific markdown features (wikilinks, embeds, callouts, frontmatter). There are no unrelated requirements (no env vars, binaries, or installs).
- Instruction Scope
- okSKILL.md contains only authoring guidance and examples for .md files; it does not instruct the agent to read local files, access system credentials, call external endpoints, or perform actions outside markdown editing.
- Install Mechanism
- okThere is no install spec and no code to install or execute. Instruction-only skills write nothing to disk and introduce minimal risk.
- Credentials
- okSkill declares no environment variables, credentials, or config paths. Nothing in the instructions attempts to access secrets or unrelated services.
- Persistence & Privilege
- okThe skill is not marked always:true and is user-invocable. It does not request persistent or elevated privileges or modify other skills/configuration.