Back to skill

Security audit

Hadith Verifier

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently verifies hadith text using disclosed local Python scripts and a public hadith dataset, with no evidence of hidden persistence, credential access, or destructive behavior.

Before installing, understand that verification depends on downloading public hadith datasets from jsDelivr/fawazahmed0 and that the tool is an aid, not a scholarly authority. Review uncertain or important results manually with qualified sources.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains user-facing operating instructions almost entirely in Arabic, while the manifest description also includes English triggers. That creates a language policy concern because the skill effectively forces Arabic for core usage guidance without documenting that the skill is Arabic-only or offering a user language choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code performs cross-collection verification by issuing HTTP requests to an external service after receiving user-supplied hadith text, but the CLI output and surrounding code do not warn users that verification depends on remote network access and may expose the queried content to a third party. For a verification tool handling user-supplied religious text or potentially sensitive input, some form of disclosure would be expected under the missing-warning rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The file embeds a fixed Arabic/English language assumption in collection metadata and text-normalization logic, but there is no natural-language indication that users can choose or opt into a preferred language or locale. Because the policy calls for flagging language or locale constraints that are forced without user opt-in, this appears to be a minor policy concern.

Content

No source excerpt is available for this finding.