jj-subagent-workspaces
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to interpolate external, user-provided task descriptions into a prompt for a subagent.
- Ingestion points: The USER-FACING TASK DESCRIPTION placeholder within the Subagent prompt template in SKILL.md.
- Boundary markers: The prompt template uses structural headers (Task:, Ground rules:, Done when:) to separate the task description from the instructions.
- Capability inventory: The workflow involves shell command execution (via agent-cli or similar) and repository manipulation using the jj CLI (e.g., jj workspace add, jj commit, jj rebase).
- Sanitization: No explicit sanitization or input validation is performed on the user-provided task description before it is delegated.
Audit Metadata