future-tokens

Fail

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The README.md and install.sh files recommend a command that pipes a remote script from GitHub directly into the shell (curl | bash). This is a high-risk pattern for executing unverified remote code.
  • [COMMAND_EXECUTION]: The install.sh script performs automated filesystem modifications, including creating directories in the home path (~/.claude/) and generating new files via sed and cat.
  • [EXTERNAL_DOWNLOADS]: The installer script fetches external repository content from GitHub as a compressed archive during the setup process.
  • [PROMPT_INJECTION]: The reasoning skills (e.g., antithesize, excavate) ingest untrusted user text for analysis without employing boundary markers or instructions to disregard embedded commands, which is a common vulnerability surface for indirect prompt injection.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/jordanrubin/FUTURE_TOKENS/main/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 21, 2026, 05:12 PM
Security Audit — agent-trust-hub — future-tokens