ClawHub
Back to skill

Security audit

Bamboohr Automation

Security checks for vulnerabilities and agentic risk

Overview

This BambooHR skill is coherent and not malicious, but it handles sensitive HR records and can change employee/time-off data without strong confirmation or minimization guardrails.

Install only for users who are authorized to access and modify BambooHR data. Before using it, require the agent to minimize requested fields, avoid showing unnecessary PII, verify the exact employee or request, summarize proposed changes, and obtain explicit confirmation before any employee update or time-off status change.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables access to highly sensitive HR data, including employee and dependent information, but does not instruct the agent to present a clear privacy warning or verify user authorization before retrieving or exposing that data. In an HR context, this omission increases the risk of inappropriate disclosure of PII and benefit/dependent records to unauthorized users or in overly broad responses.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

md
- Date format is 'YYYY-MM-DD' for start and end dates
- Balances may be in hours or days depending on company configuration
- Request status updates require appropriate permissions (manager/admin)
- Creating a request does NOT auto-approve it; separate approval step needed

### 4. Update Employee Information

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documents operations that can change HR records and approve, deny, or cancel time-off requests, but it lacks a clear warning that these actions are state-changing and may materially affect employment records and employee benefits. Without an explicit confirmation step, an agent could execute consequential actions based on ambiguous or mistaken prompts, causing unauthorized HR changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.