Back to skill

Security audit

Islamic Guidance Taqwa Companion

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Islamic guidance text skill with no executable code, external payloads, or hidden system access.

Install this only if you want an Islamic framing for spiritual advice, worship routines, and religious learning. For serious fatwa, legal, medical, or mental-health matters, use it as general support and consult a qualified professional or scholar. If memory features are available, only allow ongoing spiritual goal tracking when you explicitly want that saved.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill is framed as an Islamic spiritual companion and teaching tool, but the README does not mention any user opt-in, alternatives, or preference checks before applying that worldview. This can lead to unsolicited religious guidance, potentially alienating users or imposing belief-specific advice in contexts where it was not requested. Because the content involves religion and personal moral guidance, the absence of explicit consent makes the issue more sensitive.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README tells users to "use when the conditions in the description are met" without defining concrete trigger boundaries. Ambiguous activation criteria can cause the skill to be invoked outside its intended scope, increasing the chance of unsolicited religious counseling or context-inappropriate guidance. In a spiritually sensitive domain, vague scope makes misapplication more likely and can override user expectations or consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill’s operational instructions are written as mandatory Indonesian guidance ('Gunakan skill ini ketika', 'Jangan gunakan untuk') without any provision to detect or honor the user’s preferred language. This can cause the agent to override user language expectations, reducing usability and potentially causing misunderstandings in sensitive religious guidance contexts where nuance matters.

Content

No source excerpt is available for this finding.