figure-it-out
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to design and execute workflows based on arbitrary user tasks and local state files, creating a surface for embedded instructions to influence the agent. (Ingestion points: Reads task descriptions provided by the user and state information from local checklist files at
~/.local/state/ox/checklists/<repo>-<branch>.md; Boundary markers: None; Capability inventory: Calls other skills (swarm,architect,show-me-your-work) and executes shell commands for git operations; Sanitization: No explicit sanitization or validation of the input task content is documented). \n- [COMMAND_EXECUTION]: The skill uses shell commands to manage parallel development environments (Evidence: Utilizesgit worktree addto create independent working directories for parallel sub-agents).
Audit Metadata