orchestration
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
orcaCLI to manage terminal sessions and execute commands in those terminals (e.g.,orca terminal create --command "claude",orca terminal send). - [PROMPT_INJECTION]: The orchestration system enables agents to send messages and inject instructions into the context of other agents using commands like
orca orchestration sendandorca orchestration dispatch --inject. This creates an indirect prompt injection surface where a malicious or subverted agent could influence or control others within the same Orca runtime. - Ingestion points: Messages are ingested via
orca orchestration check --injectand task preambles viaorca orchestration dispatch --inject(SKILL.md). - Boundary markers: No specific delimiters or safety warnings are described to distinguish between orchestration system messages and legitimate agent instructions.
- Capability inventory: Agents can create terminals, execute shell commands, and manage a task DAG via the
orcatoolset. - Sanitization: The skill does not describe any validation or sanitization of the content exchanged between agents.
Audit Metadata