Back to skill
Skillv1.0.0
ClawScan security
UAPI 步骤2 (方法二): 获取原始文本 接口 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 9, 2026, 6:29 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only wrapper for a single GET /api/raw/{id} endpoint and its files, requirements, and instructions are consistent with that purpose.
- Guidance
- This skill is coherent and only documents calling GET /api/raw/{id}. Before using it: (1) Treat the decryption key as a secret — avoid pasting it into public chat or logs; passing it in a URL query string can expose it in server logs and referer headers. (2) Prefer providing keys via a secure input mechanism if available (or verify the API supports a safer header/body method). (3) Verify you trust https://uapis.cn and its handling of secrets. (4) If you do not want the agent to make network calls automatically, disable implicit/autonomous invocation in your agent settings before enabling the skill.
Review Dimensions
- Purpose & Capability
- okThe name/description match the provided SKILL.md and reference docs: the skill only documents and wraps GET /api/raw/{id} (Clipzy). It requests no unrelated binaries, env vars, or configs.
- Instruction Scope
- okThe runtime instructions are limited to reading the included reference docs and calling the specified endpoint with the path id and a decryption key query parameter. The SKILL.md does not instruct the agent to read local files, system credentials, or other unrelated data.
- Install Mechanism
- okThere is no install spec and no code files to execute; this is instruction-only, so nothing is downloaded or written to disk by the skill itself.
- Credentials
- noteThe skill requests no platform credentials or environment variables. It does, however, document that the API requires a decryption key passed as the `key` query parameter — a sensitive secret that the user must supply. The skill does not request that key as an env var, nor does it warn about the sensitivity of placing secrets in a query string (which can leak via logs or referer headers).
- Persistence & Privilege
- okalways:false and no install activity. The agent policy file allows implicit invocation (normal), but this skill does not request elevated or persistent system privileges or access to other skills' configs.