nemo-relay-export-openinference

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of documentation (SKILL.md) and evaluation data (evals.json). There are no scripts, binaries, or automated commands included.
  • [DATA_EXFILTRATION]: No network operations or sensitive data access patterns were detected. The skill describes how to configure external tracing endpoints (e.g., Arize Phoenix) as part of its primary purpose for observability.
  • [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were found.
  • [EXTERNAL_DOWNLOADS]: No external packages or remote scripts are referenced or downloaded.
  • [COMMAND_EXECUTION]: No shell commands or subprocess executions are present in the documentation or configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 11:05 AM
Security Audit — agent-trust-hub — nemo-relay-export-openinference