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

orca-cli

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch a 'version-matched guide' using the command ORCA skills get orca-cli. The output of this command is intended to provide the agent with its operational instructions for the session.
  • Ingestion points: The agent context is updated with content retrieved from the orca CLI output during execution.
  • Boundary markers: The skill lacks explicit delimiters or instructions to prevent the agent from following unintended commands potentially present in the tool's output.
  • Capability inventory: The skill operates the orca CLI, which has broad access to manage terminals, worktrees, and embedded browsers.
  • Sanitization: No sanitization process is described for the dynamic content retrieved from the executable.
  • [COMMAND_EXECUTION]: The skill facilitates shell command execution by resolving local executables like orca, orca-ide, or orca-dev. It uses environment variables such as ORCA_CLI_COMMAND and local path detection to determine which binary to execute.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 03:55 AM