orca-cli
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill operates by executing shell commands based on environment variables or specific system conditions to interact with the Orca environment.
- [DYNAMIC_EXECUTION]: The skill instructions direct the agent to load a version-matched guide at runtime by executing
ORCA skills get orca-cli, dynamically incorporating content into the agent's context. - [INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from an external command output without providing boundary markers or sanitization.
- Ingestion points: The output of the command
ORCA skills get orca-cliinSKILL.md. - Boundary markers: No explicit delimiters are provided for the dynamically loaded content.
- Capability inventory: The agent is granted capabilities to manage worktrees, terminal sessions, repositories, and an embedded browser.
- Sanitization: No validation or filtering of the guide content is mentioned.
Audit Metadata