evidenso-research

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides standard procedural instructions for using the Evidenso MCP server tools. It correctly restricts the agent from using general knowledge or web search to ensure the accuracy of the research results through its specialized tools.
  • [COMMAND_EXECUTION]: The skill mentions the usage of the design_feedback tool which can read image files from the local disk (images=[...]). This is a legitimate functional requirement for design review tasks and does not represent an unauthorized command execution or privilege escalation risk.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: There are no signs of hardcoded credentials, sensitive file path access, or unauthorized data transmission to external servers. The tools referenced are part of the expected Evidenso service environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 03:31 AM
Security Audit — agent-trust-hub — evidenso-research