Security audit

Pndr

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Pndr productivity integration, but installing it can let an AI assistant read, change, download, and delete data in your Pndr account.

Install this only if you are comfortable giving an AI assistant access to your Pndr account. Prefer a dedicated, revocable token, keep the client secret and bearer token out of chats, screenshots, and shared config files, and require confirmation before delete, archive, bulk edit, or attachment download actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill advertises many write and delete capabilities such as deleting ideas, thoughts, lists, packages, tags, comments, and checklist items, but it does not clearly warn users that the integration can perform destructive operations on personal data. In an agentic context, missing disclosure increases the chance that a user authorizes the skill without understanding that natural-language requests or agent mistakes could permanently modify or remove data.

Credential Access

High

Category: Privilege Escalation
Content: ## Authentication Pndr uses OAuth 2.0 client credentials flow. Access tokens expire after 1 year (365 days). To refresh your token, repeat the `curl` command from step 2 and update your mcporter config with the new Bearer token.
Confidence: 90% confidence
Finding: Access tokens

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.