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, and cursor-agent. These commands are used within the scripts/reachable script to check authentication status and in SKILL.md for 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_done and escalation messages, 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 the orca CLI. 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
Risk Level
SAFE
Analyzed
Nov 18, 2026, 03:59 PM