skills/meshjs/skills/mesh-core-cst/Gen Agent Trust Hub

mesh-core-cst

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill documentation instructs users to install @meshsdk/core-cst and @meshsdk/core via npm. These packages originate from an organization not present on the trusted GitHub organizations list. This is flagged as a minor concern as it is the primary purpose of the skill.
  • PROMPT_INJECTION (SAFE): No evidence of prompt injection patterns, bypass markers, or instructions to ignore safety protocols was found.
  • CREDENTIALS_UNSAFE (SAFE): The skill contains examples for handling private keys and signatures but does not include any hardcoded credentials, API keys, or secrets. All examples use standard placeholders.
  • DATA_EXFILTRATION (SAFE): There are no patterns of unauthorized data access, sensitive file reads, or network exfiltration.
  • REMOTE_CODE_EXECUTION (SAFE): No scripts or instructions for downloading and executing remote code (e.g., piped bash scripts) were identified.
  • NO_CODE (SAFE): The skill consists entirely of markdown documentation and code snippets for reference; it does not include executable logic for the AI agent to run autonomously.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 06:02 AM