Jira Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from Jira environments, creating a potential vector for indirect prompt injection.
- Ingestion points: Issue details, sprint configurations, workflow rules, and report parameters as defined in the input metadata and templates.
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings when processing the contents of Jira issues.
- Capability inventory: The skill utilizes MCP tools to create, update, and transition issues (
jira_create_issue,jira_update_issue,jira_transition), providing a mechanism for an injection to influence project data. - Sanitization: There are no explicit sanitization or escaping protocols described for the data interpolated into templates or processed by the Jira tools.
Audit Metadata