ClawHub
Back to skill

Security audit

Torah Scholar

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a benign Sefaria-powered Jewish text research helper with disclosed public API use and no persistence or credential access.

Installers should understand that this skill sends their Torah searches, references, and themes to Sefaria's public API. The dvar Torah generator produces an outline and source suggestions, so users should review religious and textual accuracy before relying on it.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
While the code does use Sefaria to retrieve texts, links, and search results, its primary purpose is not a general Jewish text search/exploration utility as described. Instead, it is a specialized Dvar Torah generator that automatically structures output, suggests a teaching outline, emphasizes weekly parsha handling, and formats sources into a ready-made presentation. The declared description partially overlaps with the underlying data access, but it materially omits the main behavior: automated generation of a Dvar Torah framework. That makes the description inaccurate enough to count as a mismatch.

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill advertises network-backed functionality via the Sefaria API, but the manifest does not declare any explicit tool scope such as allowed tools or permissions. This creates a governance gap: reviewers and runtime policy engines cannot clearly verify or constrain outbound network use, increasing the risk of unintended external access or policy bypass if the skill is installed in a broader agent environment.

Static analysis

No suspicious patterns detected.