Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (college/major recommendations) match the SKILL.md content. No unexpected binaries, credentials, or config paths are requested — nothing disproportionate for an advice/recommendation skill.
Instruction Scope
SKILL.md contains only prompts and example outputs for recommending schools as '冲档/稳档/保档' and handling follow-up questions. It does not instruct reading system files, environment variables, or transmitting data externally. Note: the skill does not specify where admission rank/capacity data comes from, so recommendation accuracy depends on external data sources not described in the instructions.
Install Mechanism
No install spec and no code files — instruction-only. This has minimal installation risk because nothing is written to disk or fetched during install.
Credentials
The skill declares no required environment variables, credentials, or config paths, which is proportionate for an advice-only skill.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or to modify other skills. The default ability for the agent to invoke the skill autonomously is normal and not in itself a concern.
Assessment
This skill appears coherent and low-risk: it only contains runtime instructions for producing college/major recommendations and asks users to provide their exam details. Before installing, consider: (1) the skill's source/homepage is unknown — if provenance matters, prefer skills with a known author or documentation; (2) do not enter highly sensitive personal identifiers (ID numbers, full identity documents) into the skill prompts — only provide the minimal academic info needed (scores, rank, subject choices, location and preferences); (3) recommendations depend on data not described in the SKILL.md (admission ranks, last-year cutoffs). Verify any suggested schools against official admissions sources before acting; (4) test with non-sensitive or dummy inputs first to confirm the style and accuracy of outputs.Like a lobster shell, security has layers — review code before you run it.
latestvk973dbyd7d9bxq4zaemam7ex3983za37
License
MIT-0
Free to use, modify, and redistribute. No attribution required.