ClawHub
Back to skill

Security audit

Jira PAT 管理基础版

Security checks across malware telemetry and agentic risk

Overview

This Jira skill is not malicious, but it can change real Jira data using a PAT and does not clearly require user confirmation before write actions.

Install only if you are comfortable letting an agent use a Jira PAT through command-line API calls. Use a least-privilege PAT, scope it to non-critical projects where possible, avoid broad callback URLs, and require the agent to show the exact Jira write action for approval before transitions, comments, field updates, or issue creation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger condition is overly broad and mismatched to the skill's actual Jira-focused purpose, which increases the chance the agent will invoke it in unrelated contexts. Because the skill has exec capability and can perform authenticated remote operations, accidental invocation could expose Jira data or cause unintended actions against a live instance.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises actions that modify Jira state, including transitions, comments, field updates, and issue creation, but does not provide explicit warnings or confirmation requirements. In the context of a project-management skill connected to a real Jira instance, this makes unintended destructive or workflow-altering actions materially more dangerous.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The examples instruct users to use a PAT in Authorization headers for external API calls but do not warn about credential handling, shell history, logs, callbacks, or transmission risks. In a skill with exec access, this can lead to token leakage through terminal history, process listings, debug output, or unintended disclosure to remote endpoints, making the context more sensitive than ordinary documentation.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.