skills/netaart/neta-skills/neta/Gen Agent Trust Hub

neta

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A comprehensive review of the skill's instructions, metadata, and routing logic confirms it is a documentation and capability mapping tool with no malicious intent detected.
  • [EXTERNAL_DOWNLOADS]: The skill contains commands for installing sub-skills via npx skills add. These references point to the vendor's own repository infrastructure (talesofai/neta-skills) and represent standard operational procedures for this platform.
  • [CREDENTIALS_UNSAFE]: The documentation explicitly advises users to authenticate via an environment variable (NETA_TOKEN) if device login is unsupported. This guidance follows industry best practices for secure credential management rather than encouraging insecure storage of secrets.
  • [COMMAND_EXECUTION]: The shell commands included in the documentation are educational examples for skill management and do not contain obfuscated logic, privilege escalation, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 04:52 AM
Security Audit — agent-trust-hub — neta