epf-bsp-add-command

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through data ingestion.
  • Ingestion points: Reads 1C source files such as 'ObjectModule.bsl' and form modules via 'Read' and 'Glob' tools.
  • Boundary markers: Lacks delimiters or instructions for the agent to ignore potentially malicious content within the analyzed source files.
  • Capability inventory: The skill utilizes 'Edit', 'Read', 'Glob', and 'Grep' tools, enabling it to read from and write to the local filesystem.
  • Sanitization: User-provided arguments (e.g., Identifier, Representation) are interpolated directly into BSL code templates without validation or escaping, which could lead to malformed code generation if inputs are malicious.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 08:35 AM