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 in SKILL.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==0.21.0 using uvx. This is a well-known tool for this specific integration and is documented neutrally.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:39 PM
Security Audit — agent-trust-hub — jira-integration