Chargify

Security checks across malware telemetry and agentic risk

Overview

The skill appears to support legitimate billing-account work, but it exposes high-impact actions like canceling subscriptions and deleting customers without enough confirmation guidance.

Review before installing. Use only with an account whose permissions match the intended work, and require explicit approval before canceling subscriptions, deleting customers, changing billing state, or performing other irreversible customer-impacting actions.

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

Findings (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill advertises destructive operations such as canceling subscriptions and deleting customers without any warning, confirmation guidance, or guardrails. In a billing platform context, this raises the risk that an agent could execute irreversible or business-critical actions from an ambiguous or mistaken prompt, causing customer, revenue, and data integrity harm.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal