instrument-metrics

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The agent is instructed to use standard deployment tools such as helm install for Kubernetes environments to deploy the official PostHog metrics agent from the vendor's OCI registry.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official vendor libraries including posthog-node via npm and the posthog Python package via pip from standard public registries.
  • [SAFE]: The skill implements secure credential management by explicitly advising against hardcoding project tokens and instead utilizing environment variables or an authenticated Model Context Protocol (MCP) tool for configuration.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests project configuration files (e.g., package.json, requirements.txt) as a surface for platform detection, it does so within the context of standard developer tooling provided by the vendor, with no evidence of malicious redirection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:39 AM
Security Audit — agent-trust-hub — instrument-metrics