Security audit
Gpt Image2
Security checks across malware telemetry and agentic risk
Overview
This skill transparently routes user-approved image-generation requests through ClawdChat, with disclosed credential use, network transmission, and credit costs.
Install only if you trust ClawdChat and the uno-cli dependency. Before approving a generation, check the prompt, reference image URLs, image count, size, and 300-credit submit cost; avoid private or identifying content unless you accept ClawdChat's handling of that data.
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.
Static analysis
No suspicious patterns detected.