Security audit
Claude API Builder
Security checks across malware telemetry and agentic risk
Overview
This is a small instruction-only skill for Claude API development and it does not request credentials, installs, persistence, or unrelated access.
Reasonable to install if you want help building with the Claude API. Expect it to guide your agent toward official Anthropic documentation and relevant SDK patterns; review any code changes your agent makes as usual.
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
42/42 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.