framework-migration-legacy-modernize
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that ingests and processes large volumes of external code and data from a legacy system.
- Ingestion points: The legacy codebase path provided via
$ARGUMENTSis passed directly to assessment and testing subagents in Phase 1 and Phase 2. - Boundary markers: The instructions do not define delimiters or warnings to prevent subagents (like
legacy-modernizerortest-automator) from obeying adversarial instructions that might be embedded in the legacy source files being analyzed. - Capability inventory: The skill coordinates agents with broad capabilities, including writing backend code, modifying database schemas, configuring API gateways, auditing security, and updating CI/CD pipelines.
- Sanitization: There are no mentioned mechanisms for sanitizing or filtering instructions from the target codebase before they are processed by the orchestrated agents.
Audit Metadata