Security audit

Typefully

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Typefully posting skill, but it should be reviewed because it can manage public social posts and has an under-disclosed API endpoint override that could redirect API keys and content if set.

Install only if you want an agent to create, edit, schedule, or publish Typefully posts for connected social accounts. Keep TYPEFULLY_API_BASE unset unless you intentionally trust that endpoint, review the selected social set and final content before scheduling or publishing, and be aware that setup may store your Typefully API key in local or global config.

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.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access, suspicious.exposed_secret_literal

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/typefully.js:16

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: scripts/typefully.js:471