plan-kanban-tasks
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script located at
.juno_task/scripts/kanban.shto create and register tasks. This is the primary intended function of the skill and uses a controlled execution path. - [INDIRECT_PROMPT_INJECTION]: The skill reads project instructions and source code from the current worktree. This provides a surface for indirect prompt injection if the project files contain adversarial instructions, though the skill implements specific constraints on where metadata and specifications can be stored.
Audit Metadata