Skills
skills/neversight/skills_feed/agent-tools/Gen Agent Trust Hub

agent-tools

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs its own command-line interface (CLI) from the vendor's domain.
  • Evidence: curl -fsSL https://cli.inference.sh | sh in SKILL.md.
  • [REMOTE_CODE_EXECUTION]: The skill uses a shell pipe pattern to install the vendor's CLI tool.
  • Evidence: curl -fsSL https://cli.inference.sh | sh in SKILL.md.
  • [COMMAND_EXECUTION]: The skill executes local commands using the infsh binary to interact with AI services, which is the primary purpose of the skill.
  • Evidence: Multiple examples in SKILL.md such as infsh app run falai/flux-dev-lora and infsh login.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 12:29 PM