omh-ralplan-driver
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard Git commands (such as
git fetch,git remote, andgit describe) to verify the freshness and versioning of local source code repositories before they are used as context for planning tasks. These are used for project synchronization and metadata verification. - [PROMPT_INJECTION]: As an orchestration skill, it facilitates the processing and distillation of outputs from various sub-agents. This introduces a surface for potential indirect prompt injection; however, the skill explicitly mitigates this through a mandatory five-step playbook that includes human-in-the-loop review, orchestrator deep-reviews, and the distillation of raw outputs into canonical artifacts.
Audit Metadata