Security audit

Web Auto Form

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed browser form automation skill, with real risks around form submission, uploads, and extraction that are expected for its purpose.

Install this only if you want an agent to automate browser form workflows. Review each generated run before execution, especially steps that submit forms, create accounts, log in, upload local files, extract page content, disable sandboxing, enable debug output, or save failure diagnostics, because those actions and artifacts may expose sensitive data.

SkillSpector

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 (1)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The tool description explicitly encourages invocation for very broad categories like 'any multi-step browser interaction task,' which can cause an agent to select this high-impact browser automation skill in situations where less privileged tools would be safer. Because this skill can navigate, fill forms, upload files, extract content, and execute conditional logic, over-broad activation materially increases the risk of unintended account actions, data submission, or interaction with untrusted sites.

Static analysis

No suspicious patterns detected.