jira-integration

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Provides template curl commands for direct interaction with the Jira REST API. These commands are standard for the intended functionality and use user-provided environment variables for authentication.
  • [EXTERNAL_DOWNLOADS]: Recommends the installation of the mcp-atlassian package via the uvx tool. This is a legitimate dependency for establishing an MCP-based Jira connection.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted data from external sources (Jira tickets).
  • Ingestion points: Jira ticket summaries, descriptions, and comments accessed through MCP tools or REST API calls in SKILL.md.
  • Boundary markers: None identified. The skill does not define specific delimiters or instructions for the agent to distinguish between Jira data and core instructions.
  • Capability inventory: The skill allows the agent to modify the external state by adding comments, updating issues, and transitioning ticket statuses.
  • Sanitization: No explicit sanitization or input validation for ticket content is described in the skill's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:20 AM
Security Audit — agent-trust-hub — jira-integration