skills/lexluthors/orca/orca-cli/Gen Agent Trust Hub

orca-cli

Warn

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONDYNAMIC_EXECUTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The instructions explicitly direct the agent to re-run commands with escalated permissions to bypass sandbox connectivity blocks (specifically handling runtime_access_denied errors).
  • [COMMAND_EXECUTION]: The skill executes local binaries determined by environment variables (ORCA_CLI_COMMAND) or platform-specific logic (orca-ide, orca-dev), which may lead to execution of unintended local files if environment variables are manipulated.
  • [DYNAMIC_EXECUTION]: The skill uses ORCA skills get orca-cli to dynamically load a version-matched guide into the agent's context. This means the agent's instructions and behavior can be modified at runtime based on the output of a local command, which is a form of dynamic context injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 16, 2026, 02:40 AM