ClawHub

Snowsand Jira

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Jira Cloud helper, but it can make live changes to Jira data with broad routing and limited safety boundaries.

Install only if you are comfortable letting the agent use your Jira API token. Use the least-privileged Jira account or token available, and require explicit review before creating issues, updating fields, adding comments, transitioning statuses, logging work, uploading attachments, or using raw API calls.

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 (2)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The description includes very broad trigger language such as handling 'any Atlassian Jira Cloud task,' which can cause the skill to activate for a wide range of generic requests. In an agent setting, over-broad routing increases the chance of unintended invocation of a skill that can read and modify remote Jira data.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation prominently describes mutating operations—issue creation, updates, transitions, comments, and worklogs—without an explicit warning that these actions change live remote Jira data. In agent-assisted workflows, lack of a mutation warning can lead to accidental writes against production project-management systems.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal