Skills
Navigate
skills/jackson7705/skills/higgsfield-marketplace-cards/Gen Agent Trust Hub

higgsfield-marketplace-cards

Fail

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides explicit instructions to install a CLI tool by piping a remote shell script directly to an interpreter: curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh. This pattern is highly dangerous as it allows for arbitrary code execution from an external source without user review or script validation.
  • [COMMAND_EXECUTION]: The skill leverages the Bash tool to run the higgsfield CLI. It dynamically constructs commands such as higgsfield marketplace-cards create by interpolating user-provided text from the --prompt argument and file paths from the --image argument.
  • [EXTERNAL_DOWNLOADS]: The skill triggers an external network request via curl to fetch a script from a remote repository (raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh).
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface.
  • Ingestion points: User-provided strings for the --prompt flag and file paths for the --image flag (SKILL.md).
  • Boundary markers: None. The input is interpolated directly into shell command arguments.
  • Capability inventory: The skill has the capability to execute shell commands via the Bash tool.
  • Sanitization: There is no evidence of input escaping, validation, or sanitization before the data is passed to the CLI command.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 8, 2026, 03:24 PM