ClawHub
Back to skill

Security audit

Fern

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Fern read-only connector through OOMOL, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you want your agent to read Fern customer, payment account, transaction, and exchange-rate data through OOMOL. Be aware that the invocation wording is broad, so use it for explicit Fern data lookups rather than general questions about Fern; review any first-time CLI install or account connection step before running it.

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 description uses an extremely broad trigger phrase: 'Use this skill for ANY Fern request' and 'Whenever a task involves Fern, use this skill instead of calling the API directly.' This can cause over-invocation of the skill for loosely related requests, reducing agent discretion and potentially routing unnecessary sensitive queries through a connector path the user did not specifically request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.