Security audit
threadly
Security checks across malware telemetry and agentic risk
Overview
This skill coherently connects an agent to Threadly's public API for human-directed review of social reply drafts and webhook management.
Install only if you intend to let the agent read Threadly project data and, when you explicitly name a draft, record approve or reject decisions. Keep the THREADLY_API_KEY scoped and protected, and only register webhook targets you control because discovered conversation data will be delivered there until the subscription is revoked.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.