Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (汇总电商、超市与品牌优惠) align with the SKILL.md content which describes filter fields, return fields, sample queries, update cadence, and privacy notes. There are no unrelated requirements (no env vars, binaries, or config paths).
Instruction Scope
SKILL.md is limited to describing what data to return and sample prompts. It does not instruct the agent to read files, access environment variables, call unspecified external endpoints, or exfiltrate data. It includes a sensible privacy caution advising protection of personal information.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk or downloaded during install.
Credentials
The skill requires no environment variables, credentials, or config paths. There are no disproportionate or unrelated secret requests.
Persistence & Privilege
always is false (default). The skill does not request elevated persistence or to modify other skills or system-wide settings. Model invocation is allowed (default) but that is expected for normal skills and not combined with other red flags here.
Assessment
This skill is internally consistent and requires nothing sensitive, but exercise normal caution: don't provide account credentials or sensitive personal data in queries; if the skill returns links or instructions to third-party pages, verify the destination before following or entering auth info; test with non-sensitive example queries first. If you plan to give it any account-specific details for personalized suggestions, confirm why those details are needed and prefer ephemeral/test credentials.Like a lobster shell, security has layers — review code before you run it.
latestvk9754hvb0e9afwg4291h9mfygn832q1k
License
MIT-0
Free to use, modify, and redistribute. No attribution required.