JIra and Confluence

ReviewAudited by ClawScan on May 10, 2026.

Overview

This is a disclosed Jira/Confluence CLI skill, but it can use an Atlassian API token to make real changes to workspace issues and pages.

This skill appears coherent for Jira and Confluence automation. Before installing, verify the external npm package, use a limited Atlassian token or account, keep credential files private, and configure allowed commands, projects, and spaces so the agent cannot make unintended workspace changes.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Medium

#ASI02: Tool Misuse and Exploitation

What this means

If the agent uses these commands incorrectly, it could create, edit, comment on, assign, or transition Jira issues or Confluence pages in the connected workspace.

Why it was flagged

These are broad Jira and Confluence write operations. They are disclosed and purpose-aligned, but they can change business records and documentation.

Skill content

`jira-ai issue create`, `jira-ai issue transition <issue-id> <to-status>`, `jira-ai issue update <issue-id>`, `jira-ai confl create <space> <title> [parent-page]`, `jira-ai confl update <url>`

Recommendation

Use the documented settings to restrict allowed projects, commands, and Confluence spaces, and require review before write operations.

Medium

#ASI03: Identity and Privilege Abuse

What this means

The agent may act with the permissions of the configured Atlassian user, including access to issues, users, worklogs, projects, and Confluence spaces that account can reach.

Why it was flagged

The skill requires Atlassian account credentials/API token use. This is expected for Jira/Confluence access, but the token may carry the user's workspace permissions.

Skill content

JIRA_HOST=your-domain.atlassian.net
JIRA_USER_EMAIL=your-email@example.com
JIRA_API_TOKEN=your-api-token

Recommendation

Use a least-privilege Atlassian token/account where possible, keep the .env file private, and avoid granting access to more projects or spaces than needed.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installing the package will run and trust code from outside the reviewed skill artifact.

Why it was flagged

The skill instructs installing a global npm package, while the submitted artifact set contains no package code or install spec to review.

Skill content

npm install -g jira-ai

Recommendation

Verify the npm package and repository before installing, prefer a pinned version, and install it in a controlled environment if possible.