llm-subtask

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides bash scripts (bin/llm-subtask-init, bin/llm-subtask-todo, and bin/llm-subtask-idea) for project-local task file management. These scripts use standard system tools such as cp, find, and sed to create and maintain task checklists and planning documents.
  • [PROMPT_INJECTION]: The skill defines a 'Marker Command' pattern where specific strings like todo push: are recognized as triggers for task updates. These commands are a core part of the skill's workflow management functionality and do not attempt to bypass safety protocols.
  • [SAFE]: The skill operates entirely within the project's local directory structure and does not perform network operations, access sensitive credentials, or execute external code from untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:22 AM