ledger-tasks-yylo
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands via the
yyCLI to interact with the task management system, including creating, listing, and archiving tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could lead to instructions being executed by the agent.
- Ingestion points: Task bodies (via
yy ledger getandsearch), inline dependency markup, and the.juno_task/config.jsonconfiguration file. - Boundary markers: The instructions define specific markup tags like
[blocked_by]and[task_id], but they do not provide explicit delimiters or instructions for the agent to ignore other natural language commands found within task bodies. - Capability inventory: The skill has access to shell execution (
yy ledger), file reading, and file writing (via report and plan files like/external/ledger-merge-plan.json). - Sanitization: There is no evidence of sanitization or escaping of task-derived content before it is interpolated into the agent's context.
Audit Metadata