video-prompting-guide
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (HIGH): The skill contains a command pattern that pipes a remote script directly to a shell:
curl -fsSL https://cli.inference.sh | sh. This allows for arbitrary code execution from a source outside the trusted list. - [EXTERNAL_DOWNLOADS] (MEDIUM): The skill references multiple external dependencies hosted by
inferenceshvianpx skills add. These sources are not on the verified trusted organization list, posing a risk of supply chain attack or malicious package injection. - [COMMAND_EXECUTION] (MEDIUM): The skill defines
allowed-tools: Bash(infsh *), which grants the agent permission to execute any subcommand of theinfshutility. Combined with the remote installation method, this provides a broad attack surface for unauthorized system operations.
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