Security audit
Context Engineering Review
Security checks across malware telemetry and agentic risk
Overview
This is a Markdown-only review skill for auditing LLM context windows, with no executable code or hidden authority.
Before using it, avoid pasting production context logs that contain secrets, private user data, credentials, or proprietary retrieval content unless you are comfortable having those reviewed in the current agent session. The skill itself is advisory and does not add executable 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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.