design-strategist

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes marketing copy and product descriptions from the conversation to generate design recommendations. This ingestion of untrusted data is a known surface, but the skill's capabilities are restricted to design analysis and metadata generation within the agent's context.
  • [DATA_EXPOSURE]: The skill contains instructions for the agent to save its output to a specific internal path for use by subsequent agents in the workflow. This is a standard state-management practice within the platform's multi-agent environment and does not involve unauthorized data access.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 07:12 AM