jira-update

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The script automates the launch of a Chromium-based browser (such as Chrome, Brave, or Edge) to handle Atlassian SSO. It uses the node:child_process spawn method to start the browser process with specific debugging flags (--remote-debugging-port, --user-data-dir) to enable programmatic interaction via the Chrome DevTools Protocol (CDP).
  • [DATA_EXFILTRATION]: The skill uses CDP commands (Network.getCookies) to programmatically retrieve authentication cookies from the browser session. These cookies are subsequently used to authenticate REST API calls to the user-specified Jira server. The cookie extraction logic is scoped specifically to the target Jira host provided in the configuration.
  • [SAFE]: The skill implements several security best practices, including a default dry-run mode where no writes occur to Jira unless the --apply flag is explicitly provided. It also maintains a transparent audit trail in a local directory (raw/jira-updates/), storing the exact JSON payloads and issue states for review before and after execution.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 12:15 AM
Security Audit — agent-trust-hub — jira-update