ClawHub
Back to skill

Security audit

Jira集成助手-免费版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only Jira Cloud helper, but users should understand it relies on their Jira API token and may read ticket data from Jira.

Install only if you are comfortable giving the agent access to Jira through your own API token. Use a least-privilege token where possible, set JIRA_BOARD to limit project scope, and avoid using it with highly sensitive Jira projects unless your organization approves agent-mediated Jira access.

SkillSpector

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest description uses broad, generic language about being suitable for general development scenarios rather than tightly scoping the skill to Jira read-only operations. In agent ecosystems, overly broad positioning can cause the skill to be invoked outside its intended trust boundary, increasing the chance that users supply unrelated sensitive data or the agent over-applies the skill in inappropriate contexts.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation instructs users to configure Jira email, API token, and URL for calls to Jira Cloud, but it does not clearly warn that issue content and credentials are used to access a remote third-party service. Without an explicit privacy notice, users may unknowingly expose sensitive ticket metadata, internal project names, or personal data through agent-mediated API usage.

Static analysis

No suspicious patterns detected.