jira-integration
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for the agent to ingest and analyze untrusted data from external sources (Jira tickets).
- Ingestion points: Jira issue data retrieved via
jira_get_issue,jira_search, and REST API endpoints described inSKILL.md. - Boundary markers: The instructions do not provide specific delimiters or guidance to the agent to disregard instructions potentially embedded within Jira ticket descriptions or comments.
- Capability inventory: The agent is given capabilities to modify Jira state (transition issues, add comments, update fields) and execute shell commands (
curl). - Sanitization: No content sanitization or validation logic is defined for the ticket data before it is processed by the AI agent.
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of an external MCP server to enable Jira functionality.
- Finding details: Suggests installing
mcp-atlassian==0.21.0usinguvx. This is a well-known tool for this specific integration and is documented neutrally.
Audit Metadata