06-infrastructure-design

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed as an analytical and documentation tool. It focuses on drafting architecture documents and does not engage in high-risk behaviors such as arbitrary command execution, privilege escalation, or persistence mechanism installation.
  • [PROMPT_INJECTION]: The skill processes project requirements from external files, which presents a surface for indirect prompt injection.
  • Ingestion points: The agent reads SRS_Draft.md, HLD.md, and tech_stack.md to extract design constraints and metrics.
  • Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore potential adversarial commands embedded within the input project files.
  • Capability inventory: The skill combines file-reading capabilities with the ability to write analysis results to a new project file (Infrastructure_Design.md).
  • Sanitization: There is no provided mechanism for sanitizing or validating the contents of the requirement documents before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 02:46 PM
Security Audit — agent-trust-hub — 06-infrastructure-design