real-content

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is instructed to read and process external files like DESIGN.md, PAGES.md, and other project materials to inform its output.
  • Ingestion points: DESIGN.md, PAGES.md, and user-supplied project materials.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the input files.
  • Capability inventory: The skill is limited to text generation and requesting imagery from a separate imagegen skill; it lacks capabilities for command execution, file-system modification, or network requests.
  • Sanitization: No explicit sanitization or validation of the input content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 10:47 PM
Security Audit — agent-trust-hub — real-content