Breezy

Security checks across malware telemetry and agentic risk

Overview

This Breezy HR skill appears purpose-aligned, but it can affect sensitive live recruiting data without enough visible scoping or safety guidance.

Install only if you intend the agent to access Breezy HR. Use least-privilege API credentials where possible, review each proposed write action before approving it, and avoid broad HR prompts unless you explicitly want Breezy candidate or job data involved.

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: 88% confidence
Finding: The skill description is broad enough to match many generic HR-related requests, which can cause the agent to invoke this skill in situations where the user did not clearly intend to access or modify Breezy HR data. In an ATS context, over-triggering is more dangerous because actions can expose sensitive applicant information or mutate live hiring records.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill documents powerful create and update actions against a live ATS but does not warn that these operations can change production recruiting data or expose sensitive candidate information. In the HR context, missing warnings increase the chance of accidental stage changes, record edits, or other unintended actions affecting real applicants and hiring workflows.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal