ClawHub
Back to skill

Security audit

Fairing

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Fairing connector skill for reading survey responses through OOMOL, with no artifact evidence of hidden or malicious behavior.

Install this if you want Codex to retrieve Fairing survey response data through OOMOL. Before use, make sure you trust OOMOL and the oo CLI setup path, and confirm any future write or destructive Fairing action explicitly if the skill is expanded beyond read-only response listing.

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 description says to use this skill for "ANY Fairing request" and "Whenever a task involves Fairing, use this skill instead of calling the API directly," which is an overly broad trigger for invocation. This can cause the agent to invoke the skill in situations where a narrower or more appropriate path should be chosen, increasing the chance of unintended tool use and expanding the skill's operational reach beyond the minimum necessary scope.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.