taobao-mcp-benchmark
What this skill does
This skill is a benchmarking and evaluation framework for the Taobao desktop MCP tool. It is designed to systematically test the functionality of the MCP tool and generate technical evaluation reports
github/leoyeai - File System Access - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=taobao-mcp-benchmarkAssessments (2)
File System Access
File System Access via local-llm-review
scripts/generate_report.js
The script reads files from the user's home directory (e.g., '/Users/qf/.copaw/tasks/...') without explicit user consent or verification. This could potentially access sensitive user data if the direcPath Traversal Risk
Path Traversal Risk via local-llm-review
scripts/generate_report.sh
The script uses variables like $TASK_DIR and $SCREENSHOTS_DIR without validating or sanitizing the input. This could potentially be exploited to access files outside the intended directory structure iBadge
Add the Anomity scan badge for taobao-mcp-benchmark to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of taobao-mcp-benchmark? Report an issue or request a rescan.
