Volcengine Ai Misc Model Discovery
v1.0.0Discover and route Volcengine AI model capabilities. Use when users ask which model to use, need endpoint capability checks, or require model selection matrices.
⭐ 0· 948·3 current·3 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (model discovery and routing) match the SKILL.md instructions (identify task, list candidates, score, recommend). However, the skill claims it can do 'endpoint capability checks' yet provides no code, no network calls, and no credentials to perform live checks — it can only produce heuristic recommendations based on internal knowledge or user-supplied info.
Instruction Scope
SKILL.md limits the agent to task classification, listing candidate endpoints, scoring, and producing a decision table and invocation template. It does not instruct the agent to read arbitrary files, access env vars, or exfiltrate data. The instructions are general (heuristic) rather than prescriptive about contacting Volcengine APIs.
Install Mechanism
No install spec and no code files beyond short metadata and references. Nothing is downloaded or written to disk, so install risk is minimal.
Credentials
No required environment variables, binaries, or config paths are declared. This matches the instruction-only design and is proportionate for a reasoning-only model-selection helper.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent system privileges or modify other skills' configuration.
Assessment
This skill is a lightweight, instruction-only helper that provides heuristic recommendations about which Volcengine model to use. It does not perform live endpoint checks or call Volcengine APIs (no credentials, no network/install steps are included), so if you need real-time capability verification or automated routing you should look for a version that explicitly integrates with Volcengine and documents required API keys and endpoints. Because it requests no secrets and writes nothing to disk, the security risk is low — but also be aware its recommendations are only as accurate as the agent's built-in knowledge or the context you provide.Like a lobster shell, security has layers — review code before you run it.
latestvk97eemps1yyvc6nm4znttr6akn80ybs8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.