pipeline-design
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as pipeline configurations, DAG definitions, and orchestration manifests. This creates a surface for indirect prompt injection where malicious instructions embedded in these files could attempt to influence the agent's behavior.
- Ingestion points: Reads pipeline configurations, DAG definitions, orchestration manifests, and infrastructure specs (referenced in SKILL.md under Scope Constraints).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed files.
- Capability inventory: The skill explicitly states it does not execute pipelines, deploy infrastructure, or modify configurations, and it has no allowed-tools or command execution patterns identified in the source.
- Sanitization: The skill states that no user-provided values are used in commands and all inputs are read-only analysis targets.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts, executable binaries, or external dependencies.
Audit Metadata