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.
Pass5 providerslatest audit May 9, 2026
Independent checks from skills.sh's audit partners.
This skill analyzes LLM experiment results from Datadog. It follows security best practices by instructing the agent to redact PII from its output. The skill has an indirect prompt injection surface because it processes untrusted LLM inputs and outputs from experiment logs, which could contain malicious instructions designed to manipulate the analysis report.
Detected behaviors
No alerts
No issues
1 file scanned · No issues
Score: 93/100 · 2 sections analyzed