vsl-hybrid-funnel

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted user input to populate sales templates, creating a vulnerability surface for instruction injection.
  • Ingestion points: The skill uses multiple placeholders in SKILL.md (e.g., [topic], [Name], [problem], [Product Name]) that are intended to be filled with user-supplied data.
  • Boundary markers: Absent. There are no delimiters or system-level instructions provided to ensure the agent ignores potential commands embedded within the user's input.
  • Capability inventory: The skill's primary function is text and HTML generation; it does not exhibit dangerous capabilities such as file system modification, network requests, or subprocess execution.
  • Sanitization: Absent. No validation or escaping logic is defined for the external content before it is interpolated into the prompt.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:49 AM