product-changelog

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines procedures for using the infsh command-line tool to authenticate and execute remote AI applications for image creation and browser-based screenshots.
  • [EXTERNAL_DOWNLOADS]: The documentation suggests installing additional agent capabilities from the inference-sh organization using the npx skills add command.
  • [SAFE]: The skill is primarily a documentation resource and does not include any executable scripts, obfuscation, or sensitive data exposure. All tool usage is consistent with the stated purpose and leverages the well-known inference.sh platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:26 AM