Back to skill

Security audit

error-translator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Markdown instruction set for explaining technical errors in plain language, with no code execution, persistence, credential access, or hidden data flow.

Installers should understand this skill is optimized for Chinese plain-language explanations of technical errors. It may activate on broad debugging phrases, so users should provide an actual error message, traceback, or log snippet for best results.

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
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README frames the skill entirely as translating errors into colloquial Chinese (“把红字翻译成人话”) and specifies response style in Chinese without indicating that users may choose another language. This creates a locale/language policy concern because the skill appears to impose a specific language by default rather than offering opt-in or alternatives.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match many generic support requests, which can cause the skill to activate when the user did not specifically intend to invoke an error-translation workflow. This is not a code-execution issue, but it can misroute conversations, reduce response quality, and interfere with more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases include very broad requests such as "debug this" and "debug this for me," which can cause the skill to activate for tasks far beyond simple error interpretation. That increases the chance the agent routes users into a constrained skill that may over-handle general debugging, potentially producing misleading guidance or bypassing more appropriate specialized skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The usage guidance says to use the skill for broad problem statements like "the program won't run" or "deployment failed," which are not necessarily error-translation tasks. This scope ambiguity can misroute complex operational or coding issues into a skill designed only to translate errors, leading to incomplete troubleshooting, overconfident advice, or suppression of needed escalation to code/config/deployment analysis.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.