email-design
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- Unverifiable Dependencies & Remote Code Execution (CRITICAL): The skill performs piped remote execution. Evidence:
curl -fsSL https://cli.inference.sh | sh. The domaincli.inference.shis not in the trusted source list. This pattern allows a remote actor to execute arbitrary code on the user's machine with the same permissions as the process running the command. - External Downloads (HIGH): The skill fetches content from an external, untrusted URL without verification or integrity checks (e.g., checksums).
- Command Execution (HIGH): The skill invokes the system shell (
sh) to execute unverified content fetched over the network, bypassing local security controls and auditing.
Recommendations
- CRITICAL: Downloads and executes remote code from untrusted source(s): https://cli.inference.sh - DO NOT USE
- AI detected serious security threats
Audit Metadata