exploring-mcp-tool-usage

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analyzed the skill for malicious patterns including prompt injection, data exfiltration, and obfuscation. No security issues were detected.
  • [COMMAND_EXECUTION]: The skill references the use of posthog:execute-sql to perform advanced analytics queries against PostHog data. This is a legitimate administrative function for the PostHog platform.
  • [DATA_EXFILTRATION]: The skill retrieves tool usage analytics, including user identifiers (names and emails) and agent intents. As these resources belong to the PostHog vendor infrastructure and are used for their stated analytical purpose, this does not constitute unauthorized data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 08:11 PM
Security Audit — agent-trust-hub — exploring-mcp-tool-usage