orca-orchestration

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the orca command-line interface to perform its core functions, including creating worktrees, managing orchestration tasks, and merging pull requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided tickets or requirements to generate task specifications that direct automated worker agents.
  • Ingestion points: The orca orchestration task-create --spec command in SKILL.md accepts a string representing the worker task specification derived from external sources.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when interpolating requirement data into the task specification.
  • Capability inventory: The orchestration system has the ability to execute shell commands, manage repository state (commits/pushes), and merge pull requests via the orca CLI.
  • Sanitization: There is no mention of sanitizing or validating the content of the ticket or requirement before it is passed to the orchestration task.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:56 AM