ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed around the use of the
infsh(inference.sh) command-line tool. It uses Bash to execute these commands for running various AI models (such as FLUX, Veo, and Claude) to generate content. - [EXTERNAL_DOWNLOADS]: The documentation references a remote installation guide for the CLI hosted on GitHub (
raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md) and provides commands to install additional skill modules usingnpx. These are legitimate references for the software's ecosystem. - [DATA_EXFILTRATION]: The skill transmits user-provided prompts to remote AI models via the inference.sh platform. This network activity is the primary purpose of the skill and is documented for the user.
- [SAFE]: No malicious patterns such as credential theft, privilege escalation, or obfuscation were detected. The file access performed (writing results to JSON files) is standard for local content creation workflows.
Audit Metadata