higgsfield-marketplace-cards

Fail

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the official CLI tool from the vendor's GitHub repository using a shell script.
  • [REMOTE_CODE_EXECUTION]: The bootstrap process involves fetching an installation script from https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh and piping it directly to a shell for execution.
  • [COMMAND_EXECUTION]: The skill uses the higgsfield CLI tool via Bash to generate marketplace assets. It constructs shell commands that incorporate user-provided prompt strings and image paths.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where untrusted data could influence agent behavior.
  • Ingestion points: User-provided product descriptions (--prompt) and image references (--image) in SKILL.md are interpolated into shell commands.
  • Boundary markers: No explicit delimiters or instructions are used to separate user-provided content from the command structure.
  • Capability inventory: The skill has access to the Bash tool and executes the higgsfield CLI as specified in SKILL.md.
  • Sanitization: No client-side sanitization or validation of the user input is described in the instruction set, although the skill notes that prompt enhancement is handled by the backend.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 27, 2026, 08:42 PM