linkedin-content

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] The skill references a shell script hosted on GitHub (raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md) for installing the belt CLI. Per the security guidelines, this is a vendor-managed resource and is considered safe.
  • [COMMAND_EXECUTION] The skill documents the use of the belt CLI tool (e.g., belt login, belt app run) to perform content research and image generation. These commands are typical for a CLI-based tool and do not involve unauthorized access or sensitive data exfiltration.
  • [SAFE] The skill predominantly consists of non-executable content, such as LinkedIn writing strategies, hook formulas, and algorithm optimization tips, which pose no technical security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:09 PM
Security Audit — agent-trust-hub — linkedin-content