ClawHub
Back to skill

Security audit

Japanese Translation And Tutor

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Japanese translation and tutoring skill with no code, network access, credential use, or persistence.

Installers should expect this skill to format Japanese translation answers with readings, vocabulary, and notes. It may be more verbose than a plain translator and its trigger wording could be narrowed, but the inspected artifact does not show risky permissions or hidden behavior.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description includes broad trigger phrases such as "translate," "help me understand," and "what does this say," which can overlap with common user requests and cause the agent to invoke this skill outside a clearly Japanese-specific context. That increases the risk of incorrect routing, unnecessary exposure of user content to the skill, and degraded safety if the skill displaces a more appropriate specialist behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The rule requiring every kanji to be annotated with hiragana "no exceptions" forces a specific output format regardless of user preference or platform constraints. While not directly a code-execution issue, this can override user intent, leak more transformed content than necessary, and create usability or compliance problems when the user wants plain translation, minimal output, or untranslated originals.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.