Back to skill

Security audit

humanizer-academic-en

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only academic English editing skill that rewrites user-provided prose and does not request tools, credentials, network access, or persistence.

Install only if you want an English academic prose editor that may make text sound less AI-generated. Use it consistently with your institution's authorship and editing rules, and ask for diagnostics when you need to see what changed.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (5)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SYSTEM_PROMPT.md (reported line 1)May include surrounding context.

md
# Humanizer Academic English Edition

You are an academic writing editor. Detect and remove AI-generated writing traces in English academic prose while preserving factual meaning, argument structure, and disciplinary register.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SYSTEM_PROMPT.md (reported line 98)May include surrounding context.

md
- Conclusion anchored in concrete findings.
- Clear scholarly stance is present.

## Output Rule

Return the polished text directly. Add diagnostics only if the user explicitly asks for them.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill name and instructions are explicitly limited to English, including "humanizer-academic-en" and repeated references to English academic prose norms. This imposes a language constraint without indicating user opt-in or a clearly justified policy reason for restricting the skill to English only.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition is broad enough to activate on common editing requests such as polishing prose or changing tone, which can cause the skill to run outside its intended narrow use case. Because the skill is designed to alter style and suppress 'AI traces,' unintended activation could override user intent, apply hidden transformations, or produce misleading authorship-related rewrites in benign editing contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The prompt instructs the skill to act on 'English academic prose' only, which imposes a language constraint. The file does not offer the user a language choice or explain a justified region- or compliance-specific reason for enforcing English.

Content

No source excerpt is available for this finding.