exploring-autocapture-events

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and SQL templates for analyzing PostHog $autocapture data. All external references point to local files within the skill package (./references/elements-chain-format.md, ./references/example-queries.md).
  • [DATA_EXPOSURE]: The skill queries the events table, which is the primary intended use case for PostHog analytics. It does not attempt to access sensitive system files (e.g., SSH keys, AWS credentials) or environment variables. The use of standard properties like $current_url and $el_text is consistent with web analytics best practices.
  • [COMMAND_EXECUTION]: There are no shell commands or subprocess executions. The skill operates entirely through SQL queries (HogQL) and JSON-based query definitions for PostHog's API.
  • [PROMPT_INJECTION]: The instructions are clear and do not contain attempts to override safety filters or bypass agent constraints.
  • [OBFUSCATION]: No obfuscated content, base64 strings, or hidden characters were detected in the files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:01 PM
Security Audit — agent-trust-hub — exploring-autocapture-events