product-intent-clarifier

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied product ideas and client requests to generate a product intent brief, which constitutes an ingestion surface for untrusted data.
  • Ingestion points: User input provided to the product-intent-clarifier (SKILL.md).
  • Boundary markers: Absent; there are no specific instructions to the agent to treat the input as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill is limited to text generation and markdown output; it does not utilize subprocesses, file-writing tools, or network operations.
  • Sanitization: Absent; the skill does not perform explicit sanitization or filtering of the user-provided concepts.
  • [EXTERNAL_DOWNLOADS]: The skill references an external documentation URL in the 'See also' section of SKILL.md.
  • Evidence: https://frontendguide.dev/docs/product-designer-first
  • Context: The link points to a developer guide and is intended for informational purposes for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 08:41 PM
Security Audit — agent-trust-hub — product-intent-clarifier