orca-per-workspace-env

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to resolve and execute a local Orca binary. Depending on the environment, it uses orca, orca-dev, or orca-ide. These are vendor-provided CLI tools used for environment orchestration.
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to fetch and follow instructions provided dynamically by the ORCA skills get command. This establishes a runtime ingestion point for instructions.
  • Ingestion points: Output of the shell command ORCA skills get orca-per-workspace-env (in SKILL.md).
  • Boundary markers: None explicitly defined in the stub instructions to delineate the fetched guide from other context.
  • Capability inventory: The agent is authorized to run shell commands via the ORCA executable, including status checks and diagnostic commands (ORCA status, ORCA vm recipe doctor).
  • Sanitization: No specific sanitization or validation of the fetched instruction set is described in this bootstrap file.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 09:29 AM