atlassian-templates
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface where external input could potentially influence agent behavior. * Ingestion points: Stakeholder interviews and requirements (SKILL.md) and template change requests (governance-framework.md) enter the agent context. * Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed data. * Capability inventory: The skill uses MCP tools like confluence_create_page, confluence_update_page, and jira_update_field_configuration to modify platform state. * Sanitization: No sanitization or validation logic is specified for input data before it is incorporated into templates.
- [SAFE]: The Python script scripts/template_scaffolder.py is a standard utility using only built-in libraries for local string generation.
- [SAFE]: No credentials, persistence mechanisms, or obfuscated contents were identified.
Audit Metadata