synthetic-users

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes research guides as input to generate simulated user personas and pilot scripts. If these guides contain instructions from untrusted sources, they could influence the agent's behavior.
  • Ingestion points: Research guides sourced from the ux-research skill or external user input (SKILL.md).
  • Boundary markers: The instructions do not define explicit delimiters or security markers to separate untrusted guide content from the agent's instructions.
  • Capability inventory: The skill writes files to the research/ directory in the local workspace (SKILL.md).
  • Sanitization: There is no evidence of sanitization or filtering applied to the ingested research guide content.
  • [EXTERNAL_DOWNLOADS]: The documentation includes commands to fetch and install additional tools and skills from the author's GitHub repository (pedroromeroluna/ai-first-product-skills).
  • [COMMAND_EXECUTION]: The skill provides instructions for the user or agent to execute npx commands to manage and install the suite of research tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 05:23 AM
Security Audit — agent-trust-hub — synthetic-users