Back to skill
Skillv1.0.0
ClawScan security
Nanjing · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 16, 2026, 1:12 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is a small, instruction-only 'knowledge card' for 'nanjing' and its requested capabilities and resources are proportionate and consistent with that purpose.
- Guidance
- This skill is small and internally consistent, but it provides only a template and likely relies on the agent's internal knowledge. Before using for decisions, ask the skill (or agent) for explicit sources/citations and clarify what 'nanjing' refers to (city, organization, person, etc.). If you require authoritative or up-to-date information, cross-check with official publications or industry reports because the skill does not fetch or cite external sources.
Review Dimensions
- Purpose & Capability
- okName/description promise quick facts about 'nanjing' and the skill contains only a short template for presenting such facts. It does not request unrelated credentials, binaries, or config access.
- Instruction Scope
- okSKILL.md only defines when to read (user searches for 'nanjing' or asks for basic info) and provides a simple template/table for facts. It does not instruct the agent to read files, access environment variables, call external endpoints, or exfiltrate data.
- Install Mechanism
- okNo install spec and no code files — instruction-only. Nothing will be written to disk or fetched during install, minimizing risk from installation mechanisms.
- Credentials
- okNo environment variables, credentials, or config paths are requested; the declared requirements are minimal and appropriate for a content/template skill.
- Persistence & Privilege
- okSkill does not request always-on presence and uses default autonomous-invocation behavior. It does not ask to modify system or other skills' configurations.