ClawHub
Back to skill

Security audit

Moesif

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Moesif connector wrapper with read-only listed actions and no artifact evidence of hidden or destructive behavior.

Install this only if you want an agent to read Moesif data through your OOMOL-connected account. Review OOMOL CLI installation and account-connection behavior first, and avoid using it for casual Moesif discussion where connector access is not intended.

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 (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description says to use this skill for "ANY Moesif request," which is an overly broad trigger that can cause the agent to invoke the skill for routine mentions of Moesif rather than only when connector-backed data access is actually intended. Overbroad routing increases the chance of unnecessary external data access, accidental disclosure of user context to the connector path, and bypass of more precise user-intent checks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.