Security audit
Tamp
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed setup guide for a local Anthropic compression proxy, with expected sensitive handling of model traffic but no hidden or malicious behavior in the skill text.
Install only if you trust or have reviewed the Tamp npm package and are comfortable routing Anthropic prompts, tool outputs, and API headers through a local proxy. Keep it bound to localhost, avoid exposing port 7778, and enable the systemd service or TAMP_LOG only if you want that ongoing behavior.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.