omh-data-pipelines
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources like job logs and orchestrator graphs, creating a surface for indirect prompt injection.
- Ingestion points: Processes job logs, Airflow DAGs, and dbt manifests as defined in SKILL.md and references/pipeline-method.md.
- Boundary markers: No specific delimiters or instructions are provided to distinguish external content from the agent context.
- Capability inventory: The skill utilizes the omh CLI tool for status recording.
- Sanitization: No validation of the ingested external content is described.
- [COMMAND_EXECUTION]: The skill performs local command execution to manage workflow state.
- Evidence: SKILL.md contains shell commands calling 'omh runtime record' to track the start and status of the planning task.
Audit Metadata