Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (recommend BBQ restaurants, routes, and tips) match the SKILL.md content. The skill requests no binaries, env vars, or installs—appropriate for an information/recommendation skill.
Instruction Scope
SKILL.md lists filters, return fields, route suggestions, examples, update cadence, and caveats. It does not instruct the agent to read local files, access unrelated environment variables, or send data to external endpoints. One minor note: data sources and how to obtain '实时热度' (real-time popularity) are unspecified, so the agent's behavior (web search, APIs, caching) is left to implementation.
Install Mechanism
No install spec and no code files. This minimizes filesystem and network install risks.
Credentials
No credentials, config paths, or environment variables are required — proportional and low-risk for the described functionality.
Persistence & Privilege
always is false and the skill does not request elevated or persistent privileges. Autonomous invocation is allowed by default on the platform but is not combined with other concerning privileges here.
Assessment
This skill is coherent and low-risk: it only contains instructions for producing BBQ recommendations. Before installing, consider: (1) where the agent will fetch 'real-time' popularity and verification (web search, third‑party APIs)—ensure those data sources are acceptable; (2) test example queries to confirm results are up-to-date and accurate; and (3) be cautious about acting on booking/payment suggestions coming from the agent (verify on the vendor's official site). If you want tighter control, restrict autonomous actions or review the agent's web/API access policies.Like a lobster shell, security has layers — review code before you run it.
latestvk97e6wnbr38v2rqgjbgz0t3x0n83ckyx
License
MIT-0
Free to use, modify, and redistribute. No attribution required.