character-design-sheet
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- Remote Code Execution (CRITICAL): The skill utilizes the pattern
curl -fsSL [URL] | sh, which downloads a script fromhttps://cli.inference.shand executes it directly. This pattern provides no opportunity for the agent or user to verify the content before execution, allowing the remote server to take full control of the environment. - External Downloads (HIGH): The source
cli.inference.shis not a trusted entity within the provided [TRUST-SCOPE-RULE]. Downloading and executing content from unverified third-party domains is a primary attack vector for system compromise. - Command Execution (HIGH): The use of piped shell execution bypasses standard security review processes and allows for the execution of obfuscated or dynamic payloads that can change at the attacker's discretion.
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