Security audit
LLM Trace → Phoenix
Security checks across malware telemetry and agentic risk
Overview
Prompt-injection indicators were detected in the submitted artifacts (system-prompt-override); human review is required before treating this skill as clean.
Install this only if you want comprehensive LLM observability and are comfortable with Phoenix storing full prompts and responses. Keep the default localhost endpoint for private use, or secure any remote Phoenix deployment with HTTPS, authentication, access control, and appropriate retention policies. ClawScan detected prompt-injection indicators (system-prompt-override), so this skill requires review even though the model response was benign.
VirusTotal
52/52 vendors flagged this plugin as clean.
Static analysis
No suspicious patterns detected.