ClawHub

Metrika Analysis

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Yandex.Metrika reporting skill that uses expected analytics credentials and does not show hidden execution, persistence, or data-changing behavior.

Install only if you intend the agent to read Yandex.Metrika analytics for the specified counter. Prefer a read-only or least-privilege token, confirm ambiguous analytics requests before using the token, and rotate the token if it is no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description is broad enough to match generic analytics or reporting requests without clearly constraining scope to Yandex.Metrika data only. In an agent setting, this can cause over-selection of the skill, leading to unintended access to analytics credentials or execution in contexts the user did not specifically authorize.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation conditions are ambiguous and do not define boundaries such as requiring explicit mention of Yandex.Metrika, a configured counter, or consent to use account-linked analytics data. This increases the chance that the skill is invoked for vague traffic-analysis questions and accesses sensitive telemetry unnecessarily.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal