twg-space-creation

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the twg CLI tool (Teamwork Graph CLI) for space and content management, as well as standard utilities like git and rg (ripgrep) for repository analysis. These commands are used to interact with the user's own environment and Atlassian services.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as Git repositories and existing Confluence spaces to inform space design. It mitigates this risk through "bounded" sampling, strict same-site enforcement for migrations, and mandatory user approval of the proposed space architecture before any creation occurs.
  • [SAFE]: The skill is authored by Atlassian and interacts exclusively with Atlassian services and tools. It follows security best practices by explicitly instructing the agent to never copy secrets, sensitive configuration, or unverified commands from source materials. It also establishes clear stop conditions for ambiguous or cross-site operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 02:20 AM
Security Audit — agent-trust-hub — twg-space-creation