create-ai-block

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill constructs prompts for an AI Block narrative by directly interpolating user instructions, creating a potential surface for instructions that could target downstream AI execution.\n
  • Ingestion points: User input regarding content requirements and output styles is processed into prompt templates in SKILL.md.\n
  • Boundary markers: The skill does not employ delimiters or specific instructions to isolate the user-provided text from the prompt structure.\n
  • Capability inventory: The skill has the capability to write to and update dashboard configuration files (AML schema), as described in SKILL.md.\n
  • Sanitization: No sanitization, validation, or escaping of user input is performed before the data is saved as a prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 09:59 AM