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.pyis 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_pagetool 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