studio-develop-migrate

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the project itself or repository exports to build a migration inventory, which could contain malicious instructions.
  • Ingestion points: The agent is instructed to read docs/PRODUCT.md, productos/develop/guides/TECH-STACK-OPTIONS.md, and the 'platform project itself' (repository exports or direct code access).
  • Boundary markers: There are no specific instructions to use delimiters or 'ignore' tags when processing content from the project being migrated.
  • Capability inventory: The skill possesses the ability to write to the file system (docs/MIGRATION.md) and perform live web research to determine export mechanics.
  • Sanitization: The instructions lack guidance on sanitizing or escaping content found in the project exports before using it to generate the migration plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:33 PM
Security Audit — agent-trust-hub — studio-develop-migrate