Security audit

Openclaw Skill

Security checks for vulnerabilities and agentic risk

Overview

This HR skill is coherent but needs Review because it can access and change sensitive employee, payroll, attendance, and compliance data without clear safety confirmations or privacy guidance.

Review this skill before installing in a real HR environment. Use only authorized HalaOS accounts and least-privilege API keys, avoid entering real employee or payroll data unless storage and privacy controls are approved, and require explicit human confirmation before payroll, approval, attendance, or compliance-form actions.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The README encourages storing and managing employee HR records locally, including salary, hire date, and jurisdiction, but does not warn users that these records contain sensitive personal and employment data. In an HR context this omission is important because users may place regulated personal data in insecure local stores such as spreadsheets or files without understanding privacy, access control, retention, and breach risks.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The cloud-mode section documents extensive API access to employee, attendance, payroll, compliance, and behavioral analytics data, including burnout and flight-risk endpoints, but does not clearly warn that prompts and operations may transmit highly sensitive workforce data to an external service. Because this is an HR skill handling special-risk employment data and inference-based analytics, users could unknowingly expose confidential records or trigger compliance issues across privacy, monitoring, and cross-border data transfer regimes.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly supports handling sensitive HR and employee data such as employee profiles, salaries, attendance, leave, benefits, and compliance records, but the description does not warn users about privacy, confidentiality, or storage/transfer risks in either local or cloud mode. In an HR context, missing disclosure about sensitive-data handling can lead users to expose personal and payroll data without understanding the security implications.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The cloud-mode API surface includes high-impact operations such as payroll runs, approvals, rejections, attendance clock actions, and government-form generation, yet the skill text does not warn that these actions may have real operational or legal consequences. In an HR/payroll system, accidental or misunderstood invocation could alter records, trigger payments, or submit compliance artifacts, creating financial, privacy, and regulatory harm.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The file includes a full section labeled in Chinese with no indication that language is optional or selected based on user preference. This can violate language/locale policy expectations when a skill presents content in a specific language without opt-in or explicit multilingual choice.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.