Back to skill
Skillv1.0.0
ClawScan security
神經科病歷助手 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 6, 2026, 1:23 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's requirements and instructions are coherent with its stated purpose (structuring neurology outpatient notes); it requests no credentials, installs nothing, and contains no code — but it lacks any guidance about handling sensitive patient data.
- Guidance
- This skill appears internally consistent and low-risk from a code/credential perspective because it is instruction-only and asks for no installs or secrets. The primary concern is privacy and clinical safety: do not feed real patient-identifiable information (PHI) unless you have guarantees about data handling, retention, and compliance (e.g., HIPAA/GDPR). Ask the publisher or platform: where is input sent (which model/provider), is any logging or storage performed, how long are inputs retained, and has the output been clinically validated? If you must evaluate, test with synthetic or de-identified notes first and confirm legal/regulatory compliance before using on real patient data.
Review Dimensions
- Purpose & Capability
- okName and description match the runtime instructions: the SKILL.md only asks the agent to accept clinical note text and output structured fields (chief complaint, HPI, exam, assessment, plan). There are no unexpected binaries, env vars, or config paths required.
- Instruction Scope
- noteInstructions stay within the stated purpose and reference only the input note and desired structured output. However, the SKILL.md does not state any policy about storage, logging, or transmission of patient-identifiable data (PHI), nor does it specify clinical validation or safety checks. This is a privacy and clinical-safety omission rather than a coherence/integrity issue.
- Install Mechanism
- okNo install spec and no code files are present, so nothing is written to disk or fetched at install time. This minimizes supply-chain risk.
- Credentials
- okThe skill declares no environment variables, credentials, or config paths. There are no requests for unrelated secrets or high-privilege access that would be disproportionate to the stated function.
- Persistence & Privilege
- okalways is false and the skill is user-invocable; it does not request permanent inclusion or modification of other skills. Autonomous model invocation is allowed by platform default but is not a unique privilege of this skill.