orchestration

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to run shell commands using the orca binary family. It provides specific resolution logic for different environments—such as managed WSL sessions, development checkouts, and standard Linux installations—to ensure the correct executable is used. Notably, it includes a safety check to avoid the GNOME Orca screen reader on Linux systems, which prevents unintended system speech output.
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a dynamic instruction fetch pattern where the agent is directed to run ORCA skills get orchestration to obtain the version-matched usage guide. This mechanism is used to keep instructions synchronized with the binary and does not show evidence of sourcing instructions from untrusted external network locations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 05:30 PM
Security Audit — agent-trust-hub — orchestration