skills/101-skills/skills/infsh-cli/Gen Agent Trust Hub

infsh-cli

Fail

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONCREDENTIALS_UNSAFE
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute a shell script from a remote URL (curl -fsSL https://cli.inference.sh | sh). This pattern allows for arbitrary code execution on the user's machine without prior inspection of the script content.
  • [DATA_EXFILTRATION]: The CLI tool documented in the skill is designed to automatically upload local files to the vendor's infrastructure. The instructions explicitly demonstrate uploading files from sensitive or broad paths such as the home directory (~/Pictures/photo.jpg) and relative paths (./screenshot.png).
  • [CREDENTIALS_UNSAFE]: The documentation encourages users to set an environment variable INFSH_API_KEY to store their API credentials. While a common practice, instructions for agents to handle these secrets increase the risk of accidental exposure during session logging or command output.
  • [COMMAND_EXECUTION]: The skill requests broad shell access via allowed-tools: Bash(belt *) to execute various CLI commands (belt app run, belt login, belt task get). This provides the agent with the capability to perform file operations and network requests through the belt utility.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 11, 2026, 06:24 PM
Security Audit — agent-trust-hub — infsh-cli