ClawHub
Back to skill

Security audit

Statsig

Security checks across malware telemetry and agentic risk

Overview

This is a read-focused Statsig connector skill that is coherent with its stated purpose and does not show hidden, destructive, or deceptive behavior.

Install this only if you want Codex to read Statsig data through an OOMOL-connected account. Review which Statsig project and scopes are connected in OOMOL, and be aware that broad Statsig requests may be routed through this skill even though its listed actions are read-only.

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
95% confidence
Finding
The trigger language is overly broad because it instructs the agent to use this skill for ANY Statsig-related request, without narrowing scope to specific read-only tasks or requiring intent matching. This can cause unintended invocation in loosely related contexts, increasing the chance that the agent routes sensitive or ambiguous requests through the skill when another workflow or additional user confirmation would be more appropriate.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.