Back to skill
Skillv1.0.0
ClawScan security
深蓝财经新闻 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 23, 2026, 7:05 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's code, instructions, and requirements are coherent with a read-only news API client and do not request unrelated credentials or elevated privileges.
- Guidance
- This skill is a read-only client for a public news API and appears coherent. Before installing: 1) confirm you trust the domain https://www.shenlannews.com (network calls will reach that host); 2) be aware that SSE endpoints may keep long-lived connections if used; 3) the agent may call the skill autonomously (platform default) — if you want to restrict automatic calls, adjust agent settings; 4) if you require auditability, inspect runtime logs to confirm only expected GET requests are made. If you need stronger guarantees, request a formal provenance or signing of the skill from the publisher.
Review Dimensions
- Purpose & Capability
- okName/description match the implementation: the SKILL.md documents public news endpoints and the included Python client issues only GET requests to https://www.shenlannews.com/api/v2. Requiring python3 is reasonable for the provided script.
- Instruction Scope
- okRuntime instructions and examples only describe querying the public API and how to compose responses. They do not instruct reading local files, accessing unrelated environment variables, or sending data to third-party endpoints beyond shenlannews.com. The only minor mismatch: SKILL.md documents an SSE stream endpoint but the included CLI client does not implement SSE consumption (not a security issue).
- Install Mechanism
- okNo install spec; the package is instruction-only with a small Python script. No downloads from external/untrusted URLs or archive extraction are present.
- Credentials
- okNo environment variables, credentials, or config paths are required. The skill does not request unrelated secrets or access tokens.
- Persistence & Privilege
- okalways is false and the skill does not request persistent system modifications. It is user-invocable and may be called autonomously by the agent (platform default), which is expected for a skill.