orca-workers
Pass
Audited by Gen Agent Trust Hub on Nov 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with local environments by executing several AI CLI tools, including
orca,claude,codex,grok, andcursor-agent. These commands are used within thescripts/reachablescript to check authentication status and inSKILL.mdfor managing project worktrees. - [INDIRECT_PROMPT_INJECTION]: The skill serves as an orchestration layer that ingests and processes content generated by external sub-agents (workers), creating a surface for indirect prompt injection. 1. Ingestion points: Data enters the agent's context through asynchronous
worker_doneandescalationmessages, as well as report files stored in/tmp. 2. Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between its own instructions and potentially malicious instructions embedded in worker outputs. 3. Capability inventory: The skill has the capability to execute shell commands and perform file system operations (worktree removal) using theorcaCLI. 4. Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the data returned by workers before it is processed.
Audit Metadata