higgsfield-soul-id
Fail
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructions include a command to download and execute a script directly from the internet:
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh. Executing remote scripts via piped shell is a critical security risk as it bypasses local review and executes arbitrary code in the user's environment.\n- [COMMAND_EXECUTION]: The skill uses theBashtool to run commands that incorporate user-supplied input, such as the<name>and<id>arguments (e.g.,higgsfield soul-id create --name "<name>"). If the agent does not sanitize these variables, an attacker could provide a name containing shell metacharacters to execute arbitrary commands.\n- [EXTERNAL_DOWNLOADS]: The skill depends on a CLI tool hosted on an external, non-whitelisted GitHub repository (higgsfield-ai/cli). This introduces a dependency on third-party infrastructure that is not associated with the skill author or established trusted vendors.
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