Back to skill
Skillv0.1.1
ClawScan security
omarchy · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 12, 2026, 4:54 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's requirements and runtime instructions are internally consistent with its stated purpose (an Omarchy-specific guardrail for running local omarchy-* scripts); it only directs static inspection of a local omarchy script directory and does not request credentials or install code.
- Guidance
- This skill appears coherent: it guides the agent to prefer and inspect local omarchy-* wrapper scripts instead of running raw system commands, and it doesn't request credentials or install code. Before installing, confirm that this host actually uses Omarchy and that the hard-coded path (/home/achals/.local/share/omarchy/bin) matches your environment; otherwise the skill may attempt to read a different user's home-path or be ineffective. Also review the actual scripts in the referenced directory (and their header comments) so you trust what the agent may propose running, and be cautious about granting the agent autonomous execution rights if you do not want it to run local scripts without approval.
- Findings
[NO_REGEX_MATCHES] expected: This is an instruction-only skill with no code files, so the static regex scanner had nothing to analyze. That absence of findings is expected and not evidence of safety by itself.
Review Dimensions
- Purpose & Capability
- okThe name/description say this is an Omarchy operating-mode guardrail for local system tasks and the SKILL.md only instructs the agent to prefer and inspect local omarchy-* wrapper scripts. There are no unrelated env vars, binaries, or install steps requested, so the requested capabilities align with the described purpose.
- Instruction Scope
- noteThe instructions direct the agent to statically inspect and prefer scripts under /home/achals/.local/share/omarchy/bin and to use read-only/status commands before taking impactful actions. This is appropriate for a local guardrail, but the path is hard-coded to a specific home directory ("/home/achals"), which may not match other hosts and could cause the agent to read a user's home files. The SKILL.md explicitly warns not to run scripts until sure, and discourages bulk probing, which reduces risk.
- Install Mechanism
- okNo install specification or code is included (instruction-only). That minimizes disk-write/execution risk and is proportional for a guidance/guardrail skill.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths. Its instructions only reference a local script directory relevant to the stated purpose, so the level of access requested is proportionate.
- Persistence & Privilege
- okThe skill is not marked always:true and does not request persistent system changes or modify other skills. Autonomous invocation is allowed by platform default, but that is not excessive given the skill's benign, local-scope purpose.