orca-per-workspace-env
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to resolve and execute a local system binary (e.g.,
orca,orca-ide, ororca-dev) based on the operating system and environment variables likeORCA_CLI_COMMANDorORCA_DEV_REPO_ROOT. - [DYNAMIC_EXECUTION]: The instructions require the agent to dynamically substitute a placeholder (
ORCA) with the resolved executable path before performing operations, which involves runtime command assembly. - [INDIRECT_PROMPT_INJECTION]: The skill implements a pattern where the actual logic is fetched at runtime via
ORCA skills get orca-per-workspace-env. The agent is instructed to treat this external output as its primary guide, creating an injection surface if the binary's output is manipulated. - Ingestion points: The output of the shell command
ORCA skills get orca-per-workspace-env(described in SKILL.md). - Boundary markers: Absent; the skill explicitly directs the agent to "Load the full guide" and follow it as the authoritative version-matched reference.
- Capability inventory: Execution of shell subcommands (status, doctor, skills get) via the resolved Orca binary.
- Sanitization: None; the agent is expected to trust and follow the instructions returned by the binary output.
Audit Metadata