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 higgsfield CLI command.
  • Boundary markers: While the command examples show the --prompt argument 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 Bash tool 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
Risk Level
HIGH
Analyzed
May 5, 2026, 10:43 AM
Security Audit — agent-trust-hub — higgsfield-product-photoshoot