陈列货盘分析
Analysis
The skill mostly matches its retail analysis purpose, but it imports an undeclared helper from a hardcoded developer-local path, so users should review it before installing.
Findings (2)
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.
sys.path.insert(0, '/Users/yangguangwei/.openclaw/workspace-front-door') from api_client import get_copilot_data
The skill loads api_client from a hardcoded absolute path outside the provided files, while the manifest only includes SKILL.md and analyze.py. That helper is not reviewable in the supplied artifacts.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
data = get_copilot_data(f'/api/v1/store/dashboard/bi?storeId={store_id}&fromDate={from_date}&toDate={to_date}')The skill retrieves store dashboard BI data for a supplied store and date range. This is aligned with the stated analysis purpose, but it still involves business/customer funnel data through the user's account context.
