ai-podcast-creation
Fail
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- REMOTE_CODE_EXECUTION (HIGH): The skill contains the command
curl -fsSL https://cli.inference.sh | sh, which downloads and executes a script from an external, untrusted source directly in the system shell. This is a classic RCE pattern as the contents of the script are not verified prior to execution. - EXTERNAL_DOWNLOADS (MEDIUM): The skill utilizes
npx skills addto install additional components from theinference-sh/skillsnamespace. These dependencies are not from a verified trusted source. - COMMAND_EXECUTION (MEDIUM): The skill makes extensive use of the
infshcommand-line interface to invoke remote applications (infsh app run). This creates a dependency on remote execution environments where the actual logic is opaque and controlled by an external provider.
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