instrument-product-analytics

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate development automation tasks. All instructions and reference code align with the intended purpose of instrumenting an application with PostHog analytics.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install PostHog SDKs from official registries (npm, PyPI, RubyGems, etc.) and references documentation from posthog.com. These are trusted or well-known sources.
  • [COMMAND_EXECUTION]: The skill executes standard package manager commands (e.g., npm install, pip install, bundle install) and interacts with the PostHog MCP server to configure the project environment.
  • [PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection due to its automated analysis and modification of project files.
  • Ingestion points: The agent is instructed to read 10 to 15 files from the project codebase (SKILL.md, Step 5).
  • Boundary markers: Not explicitly defined for the ingestion of project code.
  • Capability inventory: The skill can execute shell commands for package installation (Step 3) and perform file system writes for configuration and instrumentation (Steps 6, 9).
  • Sanitization: Not mentioned, although the modifications are targeted and minimal by design.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 11:55 PM