skills/amit-t/skills/design-interview/Gen Agent Trust Hub

design-interview

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions in SKILL.md direct the agent to read and synthesize information from multiple external markdown files and user-provided text, creating an attack surface for indirect prompt injection.
  • Ingestion points: The agent reads from project directories including context-library/prds/, context-library/business-asks/, context-library/personas/, context-library/brand/, and context-library/design-system/.
  • Boundary markers: The skill lacks explicit instructions or delimiters (such as triple quotes or XML tags) to help the agent distinguish between its core instructions and the potentially untrusted content of the context files.
  • Capability inventory: The skill's documented capabilities are limited to file reads and writing the output brief to the outputs/ directory; it does not utilize high-risk tools like shell execution or network access within its own instructions.
  • Sanitization: No sanitization, filtering, or validation steps are defined for the data extracted from context files before it is processed and summarized by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 04:28 PM