higgsfield-product-photoshoot
Fail
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill's bootstrap instructions include a command to download and execute a shell script from a remote URL:
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh. Piped execution of remote scripts bypasses standard security reviews and package management protections, posing a significant risk if the source repository is compromised. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8):
- Ingestion points: User-provided answers from the "pre-generation interview" and uploaded image paths are used as inputs for the
higgsfieldCLI command. - Boundary markers: While the command examples show the
--promptargument wrapped in double quotes, the instructions lack explicit directives for the agent to sanitize, escape, or validate the content of these strings. - Capability inventory: The skill utilizes the
Bashtool to execute shell commands, providing a bridge between untrusted user input and system execution. - Sanitization: No sanitization or filtering logic is present to prevent users from including malicious shell metacharacters or sub-commands in their input.
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