ClawHub
Back to skill

Security audit

Feathery

Security checks across malware telemetry and agentic risk

Overview

This Feathery integration is broad and can perform writes or deletes, but those capabilities are disclosed, scoped to Feathery, and paired with confirmation instructions.

Install this only if you intend to let your agent use your OOMOL-connected Feathery account. Review write and delete payloads carefully before approval, especially user deletion, hidden-field deletion, and submission updates. Treat the oo CLI install step like any remote installer and run it only if you trust OOMOL and need the connector.

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
92% confidence
Finding
The skill description is intentionally broad enough to capture essentially any Feathery-related request, including reads, writes, and destructive operations. In an agent-routing system, this can cause the skill to be selected too eagerly, increasing the chance that sensitive or state-changing connector actions are invoked in contexts where a narrower, more specialized skill or additional safeguards should apply.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.