China Weather
Analysis
This appears to be a straightforward China weather lookup skill, with expected notes around third-party weather APIs, optional API keys, and a user-run Python dependency install.
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.
## Step 1: Install Dependencies ```bash pip install requests ```
The skill asks the user to install the Python `requests` package without pinning a version. This is a normal dependency for an HTTP weather client, but it leaves package version and source trust to the user's Python environment.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
export QWEATHER_API_HOST="你的API_HOST" # 如:abc1234xyz.def.qweatherapi.com export QWEATHER_API_KEY="你的API_KEY"
The skill documents optional credentials for weather providers. These credentials are expected for the stated weather-query purpose, but they are not declared as required environment variables in the registry metadata.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
API_CHAIN = [
{"name": "qweather", "priority": 1, "fallback": True},
{"name": "seniverse", "priority": 2, "fallback": True},
{"name": "openweathermap", "priority": 3, "fallback": True},
{"name": "wttr", "priority": 4, "fallback": False}
]The skill discloses that weather lookups may be sent to multiple third-party weather providers. This is necessary for the feature, but it is still a user-data flow to outside services.
