Back to skill

Security audit

Islamic Knowledge Mastery

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only Islamic study and source-verification guide with no executable code or hidden install behavior.

Installers should understand that the skill is mainly Indonesian-language guidance for Islamic study and religious-source verification. Use it as an aid for sourced study, not as a substitute for qualified religious advice, and only enable progress tracking or reminders when explicitly wanted.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README says to use the skill 'when the conditions in the description are met' and defers the real criteria to another file, which is too vague for safe activation. Ambiguous triggering can cause the skill to be invoked in unintended contexts, increasing the chance of inappropriate retrieval, overbroad use, or bypass of more suitable specialized workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill content switches into Indonesian directives ('Gunakan skill ini ketika', 'Jangan gunakan') without asking for the user's preferred language. This can override user intent and reduce usability, especially in a sensitive religious guidance context where misunderstanding due to language mismatch can lead to incorrect interpretation or reliance on misunderstood instructions.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 970)May include surrounding context.

md
| Mistake | Fix |
|---------|-----|
| Mixing sources without verification | Cross-reference before citing |
| Losing exact attribution | Preserve surah:ayah / hadith refs |
| Shallow retrieval | Use structured knowledge retrieval |
| Ignoring teaching workflow | Apply structured teaching path |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 977)May include surrounding context.

md
| Mistake | Fix |
|---------|-----|
| Mixing sources without verification | Cross-reference before citing |
| Losing exact attribution | Preserve surah:ayah / hadith refs |
| Shallow retrieval | Use structured knowledge retrieval |
| Ignoring teaching workflow | Apply structured teaching path |