add-resource

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides purely instructional content for extending the PostHog platform's developer tools. It includes a dedicated section on a "safety invariant," which is a design principle ensuring the tool does not interfere with resources it does not manage.
  • [DATA_EXFILTRATION]: All network operations and API interactions described are directed toward PostHog's official infrastructure, which is legitimate behavior for a skill authored by PostHog.
  • [EXTERNAL_DOWNLOADS]: The skill suggests adding the zod library, a widely used and reputable package for data validation, to improve the reliability of API response handling.
  • [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety guardrails, or extract system prompts were detected in the instructions.
  • [COMMAND_EXECUTION]: The commands referenced (such as pnpm test and npx posthog-definitions) are standard development and project-specific utilities used for local verification and testing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:06 PM
Security Audit — agent-trust-hub — add-resource