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 execute the local 'orca' command-line utility (or variants like 'orca-dev' and 'orca-ide') to resolve the session environment and manage workspace recipes. Key commands include 'ORCA skills get' and 'ORCA open'.\n- [INDIRECT_PROMPT_INJECTION]: The agent is directed to ingest instructions from the output of a shell command ('ORCA skills get orca-per-workspace-env'). This creates a dependency on external data that could influence agent behavior.\n
- Ingestion points: Output of the 'ORCA skills get' command in SKILL.md.\n
- Boundary markers: None identified in the skill instructions to delimit the ingested content.\n
- Capability inventory: The agent is permitted to execute specific shell commands and process their textual output.\n
- Sanitization: No sanitization or validation of the command output is specified before the agent processes it as instructions.
Audit Metadata