Security audit
Langfuse
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only Langfuse helper skill that discloses its need for Langfuse credentials when live project access is required.
Install this if you want an agent to help with Langfuse integration or analysis. Provide credentials through environment variables when possible, prefer scoped or read-only Langfuse keys for read-only tasks, and remember that a live secret key may let the agent query or change Langfuse prompts, traces, scores, datasets, and related project data.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.