email-design
Fail
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- REMOTE_CODE_EXECUTION (CRITICAL): The skill triggers a detection for piped remote execution: 'curl -fsSL https://cli.inference.sh | sh'. This allows an untrusted external source to execute arbitrary commands on the system without verification.
- EXTERNAL_DOWNLOADS (HIGH): The URL 'https://cli.inference.sh' is not from a trusted GitHub organization or repository, posing a high risk for supply chain attacks.
- COMMAND_EXECUTION (HIGH): Piping remote scripts directly to a shell ('| sh') is a high-risk pattern that grants full environment access to unverified external code.
- PROMPT_INJECTION (LOW): The skill processes user-provided marketing content, which serves as an attack surface for indirect prompt injection.
- Ingestion points: Email marketing parameters in description files.
- Boundary markers: None identified in provided documentation.
- Capability inventory: Shell execution via the identified CLI tool.
- Sanitization: No evidence of input filtering or output sanitization.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata