migrate-pipeline
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external pipeline configuration data which could theoretically contain malicious instructions designed to influence the agent's behavior during the conversion process.
- Ingestion points: The skill fetches existing pipeline definitions using the
harness_gettool in Step 1. - Boundary markers: The instructions do not explicitly define boundary markers or instruct the agent to ignore instructions found within the pipeline YAML data.
- Capability inventory: The skill utilizes
harness_updatewhich allows for modifying configurations on the platform. - Sanitization: The skill implements a manual review process by presenting the v0 and v1 pipelines side-by-side before the optional update step, providing a human-in-the-loop check.
Audit Metadata