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.shand piping it directly to a shell for execution. - [COMMAND_EXECUTION]: The skill uses the
higgsfieldCLI 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) inSKILL.mdare 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
Bashtool and executes thehiggsfieldCLI as specified inSKILL.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