orca-per-workspace-env
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to resolve and execute local CLI binaries such as
orca,orca-dev, ororca-idedepending on the environment. This is standard functionality for integrating with the Orca toolset. - [INDIRECT_PROMPT_INJECTION]: The agent is directed to load and follow instructions from the output of a local command (
ORCA skills get orca-per-workspace-env). While this creates a surface where documentation generated at runtime influences agent behavior, the source is a trusted vendor tool. - Ingestion points: The output of the
orca skills getcommand is processed by the agent. - Boundary markers: No explicit markers are defined for the documentation output.
- Capability inventory: The agent is tasked with executing environment management, doctor, and status commands via the resolved binary.
- Sanitization: No specific sanitization or filtering of the fetched guide is mentioned beyond the instruction to read and follow it.
Audit Metadata