Receive Feedback
Security checks across malware telemetry and agentic risk
Overview
This skill gives an agent a structured, confirmation-based workflow for verifying and applying code review feedback, with no hidden scripts or unrelated data access found.
Install this if you want an agent to rigorously handle code review feedback and make code changes after confirmation. Review the proposed valid-item list before approving fixes, because the skill intentionally pushes the agent to fix all verified issues rather than defer them.
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
65/65 vendors flagged this skill as clean.