Security audit
Proposal Writing
Security checks across malware telemetry and agentic risk
Overview
This appears to be a normal proposal-writing guidance skill with no evidence of hidden execution, data access, persistence, or exfiltration.
This skill looks safe to install for proposal drafting. As with any writing assistant, avoid giving it confidential client, pricing, or legal details unless you are comfortable sharing that information with your agent workspace.
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.