Security audit
T2I
Security checks across malware telemetry and agentic risk
Overview
This is a simple placeholder skill that tells the agent to explain text-to-image support is not implemented yet, with no executable behavior.
This skill is safe to install as a placeholder, but it will not generate images until a future version adds a concrete API contract. Review any later version that adds endpoints, credentials, helper commands, polling, or file/network 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
39/39 vendors flagged this skill as clean.