Security audit
Tweet Writer
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only tweet-writing skill whose disclosed web research fits its purpose and does not request account access, code execution, persistence, or posting authority.
This skill appears suitable for ordinary tweet and thread drafting. Before installing, consider that it instructs the agent to use web search with your niche or topic, so avoid sharing confidential launches, client names, unreleased plans, or private metrics unless you are comfortable with those details being used in search queries. Review generated posts before publishing.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.