atlassian-setup

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Configures the environment by modifying the .mcp.json file to register the Atlassian MCP server and writing integration parameters to System/integrations/config.yaml.\n- [EXTERNAL_DOWNLOADS]: Utilizes npx to fetch and run the mcp-remote package to establish a connection with an official Atlassian endpoint at https://mcp.atlassian.com/v1/sse. These are well-known services.\n- [PROMPT_INJECTION]: Accesses Jira issues and Confluence pages, establishing a surface for indirect prompt injection from external data.\n
  • Ingestion points: Jira sprint data, assigned tickets, and Confluence documents are read and processed (SKILL.md).\n
  • Boundary markers: Not present; the skill instructions do not define specific delimiters to isolate external data within the context.\n
  • Capability inventory: Execution of shell commands via npx, reading/writing local configuration files and tokens, and performing network operations to Atlassian APIs.\n
  • Sanitization: Not present; external content is summarized and used for decision-making without explicit filtering or validation steps.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 07:14 PM
Security Audit — agent-trust-hub — atlassian-setup