skills/sahir619/orca/orca-cli/Gen Agent Trust Hub

orca-cli

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of local CLI commands through the orca binary or its variants (orca-dev, orca-ide). It provides resolution logic based on environment variables like ORCA_CLI_COMMAND and ORCA_DEV_REPO_ROOT to ensure the correct executable is used.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions as a bootloader that retrieves its full set of operating instructions at runtime by executing ORCA skills get orca-cli. This creates a surface where the agent's behavior is guided by the output of a local command.
  • Ingestion points: The output of the ORCA skills get orca-cli command is processed by the agent to define its capabilities and guide its actions.
  • Boundary markers: None; the skill explicitly directs the agent to follow the instructions retrieved from the CLI command.
  • Capability inventory: Terminal interaction, worktree management, repository operations, and browser control via the orca CLI.
  • Sanitization: None; the skill relies on the integrity of the orca executable provided in the user's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 05:57 PM
Security Audit — agent-trust-hub — orca-cli