newsletter-curation

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] The skill makes extensive use of the belt CLI tool (belt login, belt app run) to interact with the inference.sh platform. These commands are used to find content (via Tavily/Exa apps), generate images, and create social media posts. This is consistent with the skill's stated purpose and the vendor's documented ecosystem.
  • [EXTERNAL_DOWNLOADS] The skill references an installation script for the CLI (https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). Per safety rules, this is considered a safe reference to a well-known service (GitHub) related to the vendor's own tools.
  • [NO_CODE] The skill primarily consists of instructional markdown and shell commands intended for the user/agent to run via the belt CLI; it does not include complex scripts, executable binaries, or hidden logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:09 PM
Security Audit — agent-trust-hub — newsletter-curation