Back to skill

Security audit

English-follower

Security checks for vulnerabilities and agentic risk

Overview

This is a simple English-coaching prompt with no code, persistence, credentials, network access, or privileged actions.

Install this if you want chats rewritten into natural English with a brief friendly reply; avoid enabling it broadly if you do not want ordinary English conversations or multilingual messages automatically treated as English-practice material.

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
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is broad enough to activate on ordinary conversation, which can cause this skill to intercept unrelated requests and override more appropriate skills or baseline handling. In context, that can degrade routing integrity and produce unintended rewrites or enforced English coaching behavior when the user did not request it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill hard-codes English output and correction behavior without checking the user's language preference or offering an opt-in path. This can override user intent, reduce accessibility, and in a broader agent environment may cause incorrect handling of multilingual requests or accidental transformation of content the user did not want rewritten.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

Lines L12-L15 state that the entire response must be within one sentence and call this non-negotiable, but lines L24-L29 explicitly require two output lines. This is an internal intent/documentation contradiction that could mislead the model about the expected behavior.

Content

No source excerpt is available for this finding.