atlassian-templates

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines clear boundaries and governance for Atlassian content management. No malicious behaviors, exfiltration, or obfuscation were detected.
  • [COMMAND_EXECUTION]: A Python script scripts/template_scaffolder.py is included to generate template markup locally. This script uses only standard Python libraries and does not perform any risky network or system operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill uses tools to read and write from Confluence and Jira, creating a surface for potential indirect prompt injection from processed content.
  • Ingestion points: Content is retrieved from existing Confluence pages via the confluence_get_page tool and user requirements.
  • Boundary markers: Templates are structured using Confluence storage format (XHTML) and specific labels to separate system instructions from user content.
  • Capability inventory: The skill has the ability to update page content and field configurations using Atlassian MCP tools.
  • Sanitization: The skill mitigates risks through mandatory testing, previewing, and human verification steps in its workflows before any content is published or deployed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:33 PM
Security Audit — agent-trust-hub — atlassian-templates