epf-bsp-add-command
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates BSL code by interpolating user-provided arguments into templates. \n- Ingestion points: User-supplied CLI arguments (ProcessorName, Идентификатор, ТипКоманды, Представление) defined in SKILL.md. \n- Boundary markers: None identified; the skill does not instruct the agent to validate or escape input before insertion. \n- Capability inventory: Employs Read, Edit, Glob, and Grep tools to find and modify .bsl source files in the project directory. \n- Sanitization: No input filtering or escaping is implemented to prevent BSL syntax manipulation, such as breaking out of string literals via quotes.
Audit Metadata