xhs-auto-content-by-hot
Analysis
The skill’s content-generation workflow is mostly coherent, but it asks to store a user API key directly in the script, which should be reviewed before installation.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
requests.get(url, headers=headers, timeout=10) ... requests.post(API_URL, json=payload, headers=headers, timeout=60) ... with open(image_path, "wb") as f:
The script performs network calls to fetch hot topics and call the image-generation API, then downloads and writes generated images locally. These actions are disclosed and aligned with the skill purpose.
Required binaries (all must exist): none ... python3 {baseDir}/scripts/generate.py ... import requestsThe registry metadata declares no runtime requirements, while the skill documentation requires running Python and the code depends on the requests package.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
先询问使用者的字节跳动生图模型的 API Key 是什么,得到回复后,把它存入 generate.py 的 API_KEY 里面备用
The skill explicitly asks the agent to collect a provider API key and persist it in the script rather than using a declared credential, environment variable, or secret store.
