fynt-landing-design

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's 'upgrade' mode involves processing existing landing page code or TSX files provided by the user to transform them according to the Fynt quality bar (SKILL.md, improvement-playbook.md). This creates a vulnerability surface where the agent could potentially follow instructions maliciously embedded in the code comments or metadata of the input data.
  • Ingestion points: User-provided frontend code or TSX files in 'upgrade' mode.
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions within the input data.
  • Capability inventory: The skill allows for code generation and UI refactoring using standard frameworks; it does not request network access or sensitive file system operations.
  • Sanitization: No validation or sanitization of the input code is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:43 PM