migrate
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a multi-step workflow where user-supplied framework names and external research data are processed to generate code changes.
- Ingestion points: The workflow accepts
[TARGET],[FROM], and[TO]parameters which are interpolated directly into prompts for theoracle,phoenix, andplan-agentsub-agents. - Boundary markers: The agent prompts do not utilize explicit delimiters or instructions to ignore instructions embedded within the interpolated data.
- Capability inventory: The
krakenagent is authorized to implement code changes and run tests in the project environment based on the migration plan. - Sanitization: No input validation or sanitization mechanisms are defined for the migration targets or the documentation retrieved during the research phase.
Audit Metadata