sdk-craft

Pass

Audited by Gen Agent Trust Hub on May 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown and code templates. It does not contain executable logic or instructions that compromise system security.
  • [EXTERNAL_DOWNLOADS]: The skill mentions and provides configuration for well-known development tools such as tsup, unbuild, and changesets, which are standard and trusted in the software development ecosystem.
  • [CREDENTIALS_UNSAFE]: Code examples correctly demonstrate the use of environment variables and placeholders (e.g., process.env.MY_API_KEY) for handling sensitive keys, rather than hardcoding them.
  • [PROMPT_INJECTION]: No malicious prompts or instructions designed to bypass agent safety filters or override system behavior were found.
Audit Metadata
Risk Level
SAFE
Analyzed
May 21, 2026, 12:03 PM
Security Audit — agent-trust-hub — sdk-craft