ClawHub
Back to skill

Security audit

Confluence

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Confluence connector that uses OOMOL's oo CLI for read and user-confirmed write actions, with no artifact-backed signs of hidden or malicious behavior.

Install this only if you trust OOMOL as the Confluence connector provider and are comfortable letting the agent read Confluence content and perform explicit, user-confirmed page creation or updates through your connected account. Review write payloads carefully before approval.

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
94% confidence
Finding
The trigger text instructs the agent to use this skill for any Confluence-related task, which can override narrower tool-selection logic and route both read and write operations through a single broad integration. In this context, the skill exposes state-changing actions such as create_page and update_page, so an overbroad trigger increases the chance of unintended invocation and accidental data modification if user intent is ambiguous.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.