migrate-v1-to-v2
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan and process the user's project source code (e.g., Vue, TypeScript, JavaScript) using shell commands like
rg. This creates an attack surface where malicious instructions embedded in the project source code could potentially influence the agent's behavior during the migration process. - Ingestion points: The skill instructs the agent to scan the project directory and read various source files during the migration phases.
- Boundary markers: There are no specific boundary markers or instruction-delimiting warnings defined in the skill for handling the ingested code content.
- Capability inventory: The skill utilizes file system searching (
rg) and provides specific instructions for the agent to modify project source code files based on detected patterns. - Sanitization: No explicit sanitization or filtering of the ingested source code content is specified. This is noted as a characteristic of the skill's primary function as a code transformation tool.
Audit Metadata