Konto

Security checks across malware telemetry and agentic risk

Overview

Konto appears to be a straightforward finance-querying skill, but users should treat its API token and returned financial records as highly sensitive.

Install only if you trust the Konto service and intend to let the skill retrieve your financial records. Keep the API key out of shared terminals, logs, commits, and chat transcripts; restrict the token if Konto supports scopes, and redact balances or transaction details before sharing outputs.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (3)

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill is explicitly designed to query highly sensitive personal financial data from a remote service, but it provides no user-facing privacy warning, consent guidance, or explanation of what data leaves the local environment. In this context, the omission matters because examples cover bank balances, loans, investments, and transactions, which materially increases privacy risk if users run commands without understanding the exposure.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The API documentation exposes endpoints for highly sensitive personal financial data, including balances, transactions, investments, assets, loans, and a full financial summary, but provides no privacy warning, consent guidance, or safe-use constraints. In a skill context, this can normalize broad access to extremely sensitive data and encourage downstream use without adequate user awareness or data-minimization practices.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The quick reference instructs users to source a secrets file and use an API key directly in shell commands without any caution about credential exposure, shell history, environment leakage, or accidental logging. In agent or automation environments, this increases the chance that credentials are mishandled, printed, persisted, or reused insecurely.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal