Security audit

hr-indotrading

Security checks for vulnerabilities and agentic risk

Overview

This is a small Indonesian HR guidance skill that discusses sensitive employee and payroll topics but does not install code, run commands, persist data, or hide behavior.

Install only for authorized HR use. Users should avoid entering employee or payroll data unless they have permission, and should apply local privacy, labor-law, retention, and human-review controls before using the skill's red flags for personnel decisions.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The description explicitly instructs the agent to 'Berbicara profesional dalam Bahasa Indonesia,' which imposes a fixed language requirement. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific or optional.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The file defines HR monitoring integrations and explicit employee red-flag criteria without any privacy, consent, access-control, or user-impact guidance. In an HR skill handling sensitive employee and payroll contexts, this can normalize surveillance-oriented processing and lead downstream agents or operators to collect, combine, and act on employee data without proper legal basis or safeguards.

Natural-Language Policy Violations

Low

Confidence: 72% confidence
Finding: All headings and instructions in the file are written in Indonesian, but the document does not state that the skill is intended only for Indonesian-speaking users or a locale-specific deployment. This can violate language/locale policy when users are not given a language choice or opt-in.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: The entire document uses Indonesian-language headings and descriptions such as 'Komponen Payroll' and 'Jadwal Payroll', but it does not state that the skill is intended only for Indonesian users or offer any user language choice. Under the natural-language policy rule, forcing a specific language without user opt-in can be a policy violation unless the locale restriction is clearly documented and justified.

Static analysis

No suspicious patterns detected.