nextjs-app-router

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection.\n
  • Ingestion points: In basic-integration-1.0-begin.md, the agent is instructed to read 10-15 project files to identify tracking opportunities. It also suggests reading dependency source code in node_modules within the framework guidelines in SKILL.md.\n
  • Boundary markers: The workflow relies on a .posthog-events.json file for planning, which provides a structured intermediate step between reading and writing.\n
  • Capability inventory: The skill involves writing and editing project files (as seen in basic-integration-1.1-edit.md) to implement event capture and user identification.\n
  • Sanitization: The instructions do not include steps to sanitize or validate the content of the files being read before the agent acts upon them.\n- [EXTERNAL_DOWNLOADS]: The documentation in next-js.md references the use of the official PostHog wizard. This involves fetching the @posthog/wizard package from the NPM registry, which is an established and trusted repository for a well-known service.\n- [REMOTE_CODE_EXECUTION]: The skill provides instructions to execute the PostHog setup wizard using npx -y @posthog/wizard@latest. This constitutes remote code execution from a trusted service provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:33 PM