v1.0.0

low-carbon-medicine

BenignClawScan verdict for this skill. Analyzed Apr 30, 2026, 1:40 PM.

Analysis

This is an instruction-only low-carb lifestyle medicine skill with no code or credentials, but users should treat its medical and diet guidance as informational and avoid sharing unnecessary health details.

GuidanceThis skill appears technically low-risk because it is instruction-only and asks for no installation, credentials, or system permissions. Before using it, remember that it gives medical-style diet and fasting guidance; share only necessary health details and consult a qualified clinician before changing treatment, medication, fasting routines, or diet for diabetes or other medical conditions.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Human-Agent Trust Exploitation

SeverityMediumConfidenceHighStatusNote

SKILL.md

基于循证医学，以低碳水饮食为核心...帮助改善肥胖/三高/糖尿病/代谢综合征；政策：卫健委2024版已纳入低碳水为一线干预方案

The skill uses authoritative medical framing and gives disease-related lifestyle recommendations. It also includes safety boundaries such as '禁止诊断' and doctor-referral guidance, so this is a notice rather than a deception finding.

User impactUsers may place high trust in diet or fasting recommendations because they are presented in medical and policy terms.

RecommendationTreat the guidance as educational lifestyle information, and consult a qualified clinician before making major diet, fasting, diabetes-medication, pregnancy, kidney, liver, heart, or other disease-related changes.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceHighStatusNote

SKILL.md

收集：体重/身高/BMI、健康状况、用药、主要不适、体检指标

The skill instructs the agent to collect health status, medication, symptoms, and medical-test information. This is aligned with health consultation, but it places sensitive health context into the conversation.

User impactUsers may share sensitive medical details while using the skill.

RecommendationShare only the health information needed for the question, avoid personal identifiers, and do not rely on the chat as a private medical record.