yandex-metrika-assistant

• Outcome: Review
• Latest audit: May 29, 2026 at 9:29 PM UTC
• Version:
  1.0.0

Overview

This documentation-only Yandex Metrika helper appears purpose-aligned, but it should be reviewed because it encourages powerful OAuth access and includes unsafe credential examples.

Review before installing. Use your own Yandex OAuth app, prefer metrika:read for reporting, add write/import scopes only when you intend to modify counters or upload data, store tokens only in OpenClaw secrets or environment variables, never send tokens or passwords over Telegram/private messages, and require explicit confirmation before POST/PUT/DELETE, access grants, imports, or log cleanup.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Intent-Code Divergence

Medium

• Confidence: 94% confidence
• Finding: The documentation shows a full OAuth bearer token string in an HTTP example, and it is formatted like an actual credential rather than an obviously fake placeholder. In an auth-focused skill, readers may copy, reuse, or accidentally trust exposed-looking secrets, and if the token is real or was ever valid, it could enable unauthorized access to Yandex Metrika data or management APIs.

VirusTotal

66/66 vendors flagged this skill as clean.