epf-bsp-init

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates user-supplied arguments directly into source code templates. While necessary for its function as a code generator, this creates a theoretical surface for indirect prompt injection. \n
  • Ingestion points: Command arguments for ProcessorName, Type, and Destination. \n
  • Boundary markers: No delimiters separate user input from the template code. \n
  • Capability inventory: The skill is limited to reading and editing local project files via Read, Edit, Glob, and Grep tools. \n
  • Sanitization: No input cleaning or validation is performed on user arguments before they are written to the target file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 10:46 AM