ClawHub
Back to skill

Security audit

Sif

Security checks across malware telemetry and agentic risk

Overview

This Sif connector skill is coherent and purpose-aligned, with disclosed third-party calls and point costs users should be aware of.

Install this if you want agents to use your OOMOL-connected Sif account. Be aware that market-analysis calls send the relevant ASIN, keyword, or business query data to Sif/OOMOL and many listed read actions consume Sif points; review payloads before sensitive or costly requests.

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
93% confidence
Finding
The instruction to use this skill for "ANY Sif request" is overly broad and can cause an agent to invoke the connector for incidental mentions of Sif rather than only when the user explicitly wants Sif data access. This increases the chance of unnecessary third-party calls, unintended data disclosure to the connector, and avoidable consumption of paid Sif points.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.