AI tool official cli
Risk level
low
10/100

phi ↗

phi is an officially published AI tool from Pulse AI Club. Anomity scores its risk at 10 out of 100 (low).

Analysis summary

phi is an officially published AI tool from Pulse AI Club. Anomity scores its risk at 10 out of 100 (low).

Minimal Go terminal coding agent with permission gates, sub-agents, skills, and MCP

Why this entry scored 10 out of 100

This profile starts at the catalog's neutral base of 50. Because the entry is officially published, trust adjusts the score by -40. The entry declares no high-risk capabilities on its own, so capabilities add nothing. It matches no dangerous capability combinations. The clamped result is 10, placing it in the low band.

See the full scoring formula →

Findings

  • Published by the vendor Trust offset
    Contribution to score: -40

Configuration surface

Files this AI tool reads on the host. Anything written here changes what the agent does next.

  • phi-config global yaml
    User config (models, permissions, skill path)
    • win32${USERPROFILE}\.phi\config.yaml
    • darwin${HOME}/.phi/config.yaml
    • linux${HOME}/.phi/config.yaml
  • phi-mcp global json
    User MCP servers (mcp.json; Claude Desktop mcpServers migration shape also accepted)
    • win32${USERPROFILE}\.phi\mcp.json
    • darwin${HOME}/.phi/mcp.json
    • linux${HOME}/.phi/mcp.json
  • phi-project-mcp project json
    Project MCP servers (.phi/mcp.json overrides global)
    • win32${PROJECT}\.phi\mcp.json
    • darwin${PROJECT}/.phi/mcp.json
    • linux${PROJECT}/.phi/mcp.json
  • phi-skills global markdown-frontmatter
    User skills (SKILL.md)