ClawHub
Back to skill

Security audit

SG Scripture Commentary

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple scripture-commentary formatter that asks the user for a source and save path before fetching or writing content.

Install only if you want an agent to fetch or use provided scripture text and save formatted commentary files. Review the requested source URL and output path, and confirm overwrites only when intended.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
95% confidence
Finding

The trigger description is broad enough to match generic requests like 'explain this scripture' or 'write commentary' across many religious and philosophical texts, which can cause the skill to activate outside narrowly intended contexts. Over-broad activation increases the chance of misrouting user requests, causing unintended file-writing or network-fetch workflows to run when the user only wanted a simple explanation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The progress reporting section hard-codes status updates in Chinese (for example, "已完成 10%") and does not indicate that the language should follow the user's preference. This can violate language or locale policy when the user has not opted into Chinese output.

Content

No source excerpt is available for this finding.