OverviewHistoryStatsSecurity
Security
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Warn3 providerslatest audit Sep 14, 2026
Independent checks from skills.sh's audit partners.
This skill provides tools and scripts to analyze AI agent traces stored in PostHog. It allows for searching, listing, and inspecting traces to debug agent behavior. A low-risk surface for indirect prompt injection is present because the skill processes raw interaction history (user inputs and LLM outputs) which may contain malicious instructions designed to influence the agent performing the analysis.
Detected behaviors
1 alert: gptAnomaly
1 issue