atlassian-templates
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external information from stakeholder interviews, Jira queries, and user feedback to generate templates and automated content.
- Ingestion points: External data enters the agent context through stakeholder interviews, review of existing content patterns, and dynamic Jira queries as described in the workflows and MCP integration sections of SKILL.md.
- Boundary markers: The skill lacks explicit instructions for implementing boundary markers or delimiters to separate untrusted external data from the agent's instructions during template generation.
- Capability inventory: The skill utilizes Confluence and Jira MCP tools to perform file-writing and modification tasks, including creating page templates and deploying issue descriptions.
- Sanitization: There are no specified sanitization or validation protocols for data retrieved from external sources before it is interpolated into templates.
- [DYNAMIC_EXECUTION]: The skill instructions facilitate the creation and use of executable logic for automation.
- Script generation: The skill specifies building "automated template deployment scripts" and updating templates programmatically via MCP integration.
- Context: While consistent with the stated purpose of automating Atlassian workflows, the generation of scripts from templates represents a dynamic execution surface.
Audit Metadata