Back to skill

Security audit

Science Technology Research Intelligence

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only research guidance skill with no hidden code or install-time execution, though its broad scope and Indonesian instructions may require user review.

Review the Indonesian guidance before installing if you cannot read it comfortably, and only allow memory, file analysis, web research, or code execution when those tools are appropriate for the research task you asked for.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README tells users to 'Use when the conditions in the description are met' without defining concrete activation boundaries in this file. For a broad, high-capability research skill, ambiguous invocation criteria can cause overbroad or inappropriate use, increasing the chance the agent applies the skill in unsafe contexts or trusts incomplete guidance from another file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s core instructions are written in Indonesian and repeatedly direct the assistant behavior without providing a user-language negotiation mechanism. This can override or conflict with the user’s preferred language, causing misunderstanding, unsafe misexecution of tasks, or exclusion of users who cannot review the skill’s operating constraints.

Content

No source excerpt is available for this finding.