Typeform

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Typeform read-only connector, but users should treat form responses as sensitive data.

Install this only if you want an agent to read data from your connected Typeform account through OOMOL. Limit use to tasks where Typeform access is actually needed, and be careful with form responses because they can include respondent names, emails, free-text answers, or other sensitive submissions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (2)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The instruction to use this skill for ANY Typeform request is overly broad and can cause an agent to invoke the skill for loosely related tasks without first validating scope, necessity, or least-privilege access. In context, the skill is read-oriented, but the trigger language can still cause unnecessary access to Typeform account data when a user merely references Typeform tangentially.

Missing User Warnings

Low

Confidence: 91% confidence
Finding: The action documentation instructs users how to list form responses but does not warn that Typeform responses commonly contain personally identifiable information or other sensitive user-submitted content. In an agent setting, this omission can normalize broad data retrieval and increase the chance of unnecessary exposure, over-collection, or disclosure of respondent data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal