sales-enablement

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests untrusted external data, creating an attack surface where embedded instructions could influence the agent.
  • Ingestion points: The skill processes user-supplied text for product updates and explicitly instructs the agent to reference external competitive documents via @file syntax.
  • Boundary markers: The instructions lack explicit delimiting or specific guidance for the agent to ignore instructions contained within the external files being analyzed.
  • Capability inventory: The skill is designed to perform file system operations, specifically saving generated content as markdown files.
  • Sanitization: There are no defined sanitization or validation steps for the content extracted from external files before it is processed or written to new documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 11:47 PM