Security audit
Agent Content Pipeline
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed human-reviewed social content workflow, but users should treat its posting credentials and browser tokens as sensitive.
Install only if you trust the npm CLI package to handle your social accounts. Use dry runs and the secure initialization mode where possible, and never paste X auth_token or ct0 values into chats, shared files, logs, or prompts; enter them only into a trusted local CLI prompt.
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.