ux-research

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as a 'Discovery Brief' and data from a 'product node' to generate research plans. This creates a surface where malicious instructions embedded in the input data could potentially influence the agent's output.
  • Ingestion points: Processes the 'Discovery Brief' and the 'loaded product node' as primary inputs.
  • Boundary markers: The instructions do not specify any delimiters or safety markers to isolate external data from system instructions.
  • Capability inventory: The skill has the capability to write research files to the local file system (e.g., research/<YYYY-MM-DD>-research-plan.md).
  • Sanitization: No explicit sanitization or validation of the input data is mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill contains instructions suggesting the use of npx to install related tools and skills from the author's package (pedroromeroluna/ai-first-product-skills). While these resources originate from the same author, they involve executing external code at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 05:22 AM
Security Audit — agent-trust-hub — ux-research