p-image
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
infshCLI tool to run various image generation models. This execution is restricted to the specific vendor tool as defined in theallowed-toolsconfiguration.\n- [EXTERNAL_DOWNLOADS]: The skill references an installation script for theinfshCLI hosted on the vendor's GitHub repository (github.com/inference-sh). This is a standard distribution method for the author's own tooling and does not involve untrusted third-party sources.\n- [SAFE]: The skill follows secure practices for credential management by directing users to use theinfsh logincommand rather than hardcoding sensitive API keys or tokens. No signs of obfuscation, prompt injection, or unauthorized data access were found.
Audit Metadata