investigate-metric

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (compare_to_prior_periods.py and breakdown_attribution.py) to perform statistical analysis and anomaly detection on JSON data retrieved from PostHog tools. These scripts only use Python standard library modules.
  • [COMMAND_EXECUTION]: Utilizes git log to correlate metric anomalies with code changes in the local repository, which is a standard diagnostic practice in developer-oriented environments.
  • [SAFE]: All data retrieval and insight management are conducted through established PostHog MCP tools, consistent with the vendor's provided functionality and the skill's stated purpose.
  • [SAFE]: No remote code downloads, obfuscation, or unauthorized data exfiltration patterns were detected in the instructions or helper scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 05:27 PM
Security Audit — agent-trust-hub — investigate-metric