sales-enablement

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to generate sales documents based on user prompts and external data files, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: The instructions in SKILL.md direct the agent to load positioning and product data from .agents/product-marketing-context.md.
  • Boundary markers: There are no explicit delimiters or specific safety instructions (e.g., 'treat the following as data only') provided to the agent to isolate the context file content.
  • Capability inventory: The skill does not possess high-risk capabilities such as command execution, file system writing, or network communication.
  • Sanitization: The skill instructions do not include steps to sanitize, validate, or filter the content ingested from the external context file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:54 PM