migrate-to-skills
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from .mdc and .md files by copying content verbatim without sanitization. This creates an attack surface where existing malicious instructions in source files would be preserved in the migrated output.
- Ingestion points: Files matching {workspaceFolder}/**/.cursor/rules/.mdc, {workspaceFolder}/.cursor/commands/.md, and ~/.cursor/commands/*.md.
- Boundary markers: None. Instructions explicitly require verbatim copying.
- Capability inventory: File read, write, and delete operations via agent tools.
- Sanitization: None.
- [DATA_EXPOSURE]: The skill accesses the user's home directory (~/.cursor/commands/) to read configuration files. While these are not primary secrets, they contain user-defined logic and instructions which are accessed to facilitate the migration.
- [COMMAND_EXECUTION]: The skill performs destructive file operations, specifically deleting source files after migration. This behavior is consistent with the stated migration purpose but involves permanent modification of the configuration environment.
Audit Metadata