xianyu_metrics
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
bashtool to execute Python commands (python -m src.cli) within a fixed directory path (/home/node/.openclaw/workspace) to generate dashboards, daily reports, and data exports. - [PROMPT_INJECTION]: There is a potential surface for indirect prompt injection as the skill processes external data from the Xianyu platform.
- Ingestion points: The skill retrieves store data, product details, and customer inquiries via
src.cli. - Boundary markers: None explicitly defined; the agent is tasked with formatting the tool's JSON output into human-readable tables.
- Capability inventory: The agent has access to the
bashtool for command execution. - Sanitization: No specific filtering or instructions to ignore embedded commands in the source data are provided.
Audit Metadata