higgsfield-marketplace-cards
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
@higgsfield/clipackage globally via the NPM registry if it is not already present. - [COMMAND_EXECUTION]: The skill relies on the
Bashtool to perform operations such as checking account status, logging in, and triggering image generation jobs through thehiggsfieldcommand-line utility. - [PROMPT_INJECTION]: The skill is potentially vulnerable to command injection through indirect prompt injection. It takes user-provided strings for the
--promptargument and file paths for the--imageargument and interpolates them into shell commands. This creates a surface where an attacker could provide crafted input (e.g., including semicolons or backticks) to execute unauthorized commands if the agent does not properly escape or sanitize these inputs before execution.
Audit Metadata