omnibus-instrument-llm-analytics

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official SDKs for various LLM providers (e.g., OpenAI, Anthropic, Google) and PostHog's own observability libraries via standard registries like PyPI and npm.
  • [COMMAND_EXECUTION]: The skill uses standard package management commands (pip install, npm install) to set up the tracing environment. It includes instructions for the agent to perform these installations as background tasks to optimize workflow.
  • [DATA_EXFILTRATION]: The skill is designed to capture and transmit metadata related to AI generations (such as token counts, latency, and costs) to PostHog's official ingestion endpoint (https://us.i.posthog.com). This behavior is transparent, documented, and aligns with the skill's stated purpose of providing LLM analytics.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 07:14 AM