freshworks-fdk-setup-skill

Fail

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses a piped-to-shell execution pattern to install dependencies.
  • It executes a remote script from the nvm-sh GitHub repository using curl | bash to install Node Version Manager.
  • It leverages the Task tool to spawn subagents that autonomously execute shell commands based on dynamically generated prompts.
  • [EXTERNAL_DOWNLOADS]: The skill fetches resources from external repositories and CDNs.
  • Downloads the NVM installation script from GitHub.
  • Downloads FDK CLI packages from the vendor's CDN at cdn.freshdev.io.
  • Accesses the Freshworks Developers Homebrew tap for macOS installations.
  • [COMMAND_EXECUTION]: The skill performs persistent system configurations and administrative tasks.
  • Modifies user shell profiles (~/.zshrc, ~/.bash_profile, ~/.bashrc) to add environment variables (FDK_NODE_VERSION) and aliases (fdk-env).
  • Recommends that Windows users bypass execution policies (Set-ExecutionPolicy Bypass) and run sessions as Administrator for installation.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) in its argument processing.
  • Ingestion points: The version string provided as a command argument for the /fdk-setup downgrade operation in SKILL.md.
  • Boundary markers: Absent; the user-provided version string is interpolated directly into the subagent's prompt without delimiters.
  • Capability inventory: The resulting subagent has full access to the shell tool, enabling file system writes and command execution.
  • Sanitization: No validation or escaping is applied to the $ARGUMENTS before they are passed into the subagent's logic block.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 28, 2026, 11:42 AM