ClawHub
Back to skill

Security audit

Atlassian Jira by altf1be

Security checks across malware telemetry and agentic risk

Overview

This Jira skill does what it says: it lets an agent read and change Jira data using user-provided Jira credentials, with no evidence of hidden behavior.

Install only if you are comfortable giving this skill Jira API-token access. Use a least-privileged Jira account or token, verify JIRA_HOST points to your intended Atlassian site, keep the token out of shared files, and require review before allowing write, delete, attachment, or workflow-transition actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/jira.mjs:27