design-thinking

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest, synthesize, and iterate on external, untrusted data such as user research notes, design briefs, and problem statements.
  • Ingestion points: The skill explicitly instructs the agent to process raw research notes and design briefs provided by the user (as seen in the intermediate and complex prompt examples in README.md).
  • Boundary markers: There are no instructions for the agent to use specific delimiters or to ignore potential instructions embedded within the provided research data.
  • Capability inventory: The skill leverages the agent's ability to generate text and structure data based on these external inputs.
  • Sanitization: The instructions lack guidance for the agent to sanitize or filter input data, making it theoretically possible for a user to include malicious instructions within design artifacts that the agent might then follow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:07 PM
Security Audit — agent-trust-hub — design-thinking