Back to skill
Skillv1.0.0
ClawScan security
UAPI 程序员历史上的今天 接口 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 9, 2026, 7:31 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only skill that cleanly wraps a single public UAPI endpoint (GET /history/programmer/today); its requests, docs, and permissions match its described purpose.
- Guidance
- This skill is coherent and low-risk: it only documents and calls a public UAPI endpoint. Before installing, decide whether you trust the agent to make outgoing HTTP calls to the stated base URL (https://uapis.cn). Do not provide any API key unless you want the agent to use your account's quota; if you are concerned about autonomous calls, keep the skill but avoid supplying credentials or restrict agent permissions. If you need stronger assurance, verify network requests from the agent or test the skill in a sandboxed environment first.
Review Dimensions
- Purpose & Capability
- okThe skill name and description map directly to a single UAPI endpoint. It requests no credentials, no binaries, and no config paths — all proportional to a simple API-wrapper skill.
- Instruction Scope
- okSKILL.md only instructs the agent to consult local reference docs and call the specified endpoint; it does not ask the agent to read unrelated files, environment variables, or exfiltrate data. It also sensibly notes that an API key may be needed if rate limits are hit.
- Install Mechanism
- okNo install spec and no code files are included (instruction-only), so nothing is written to disk or installed. This is the lowest-risk install profile.
- Credentials
- okThe skill declares no required environment variables or secrets. It mentions that an optional UAPI Key may be needed if the anonymous quota is exhausted — that is consistent and optional, not demanded.
- Persistence & Privilege
- okalways is false and the skill does not request elevated or persistent privileges. allow_implicit_invocation is enabled in the agent interface (normal for skills) and does not by itself indicate misuse.