design-foundations

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data which could contain malicious instructions.
  • Ingestion points: The agent is instructed to read representative rendered HTML excerpts (e.g., homepage.html) and aggregate CSS/HTML analysis files from the project output directory.
  • Boundary markers: There are no explicit instructions or delimiters used to separate the ingested HTML content from the agent's instructions to ensure it is treated strictly as data.
  • Capability inventory: The skill utilizes the liberate_design_foundation_validate MCP tool and performs various file read operations across the project structure.
  • Sanitization: No sanitization, validation, or escaping of the HTML content is mentioned before the agent processes it for role assignment and evidence gathering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 09:44 PM
Security Audit — agent-trust-hub — design-foundations