Word DOCX Formatting Repair Helper

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 9:44 AM UTC
• Version: 0.1.1

Overview

This is a coherent Word/DOCX formatting helper with no bundled executable code, persistence, credential handling, or hidden data flow.

Before installing, note that the skill may activate on broad document-formatting terms, so use it for Word or DOCX cleanup tasks. For batch document edits, keep backups and dry-run reports as the skill itself recommends.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Memory Poisoning: Persistent Context Injection, Context Window Stuffing, Memory Manipulation
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Memory Manipulation

High

• Category: Memory Poisoning
• Confidence: 85% confidence

Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · README.md (reported line 18)May include surrounding context.

md

1. Clarify the target format, document count, style guide, required sections, protected content, tracked changes needs, and acceptable tooling.
2. Inspect headings, styles, numbering definitions, tables, fields, hyperlinks, images, footnotes, and section breaks before editing.
3. Choose the safest repair path: Word UI steps, python-docx, Pandoc, LibreOffice conversion, XML-level inspection, or manual style normalization.
4. Plan find-and-replace rules with examples, exclusions, backup strategy, and a dry-run report when batch changes are involved.
5. Apply or describe repairs in small reversible stages, preserving semantic styles instead of hard-coding visual formatting.
6. Render or otherwise verify page flow, headings, numbering, tables, links, and conversion fidelity.

Memory Manipulation

High

• Category: Memory Poisoning
• Confidence: 85% confidence

Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · README.md (reported line 25)May include surrounding context.

md

1. Clarify the target format, document count, style guide, required sections, protected content, tracked changes needs, and acceptable tooling.
2. Inspect headings, styles, numbering definitions, tables, fields, hyperlinks, images, footnotes, and section breaks before editing.
3. Choose the safest repair path: Word UI steps, python-docx, Pandoc, LibreOffice conversion, XML-level inspection, or manual style normalization.
4. Plan find-and-replace rules with examples, exclusions, backup strategy, and a dry-run report when batch changes are involved.
5. Apply or describe repairs in small reversible stages, preserving semantic styles instead of hard-coding visual formatting.
6. Render or otherwise verify page flow, headings, numbering, tables, links, and conversion fidelity.

Memory Manipulation

High

• Category: Memory Poisoning
• Confidence: 85% confidence

Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md

1. Clarify the target format, document count, style guide, required sections, protected content, tracked changes needs, and acceptable tooling.
2. Inspect headings, styles, numbering definitions, tables, fields, hyperlinks, images, footnotes, and section breaks before editing.
3. Choose the safest repair path: Word UI steps, python-docx, Pandoc, LibreOffice conversion, XML-level inspection, or manual style normalization.
4. Plan find-and-replace rules with examples, exclusions, backup strategy, and a dry-run report when batch changes are involved.
5. Apply or describe repairs in small reversible stages, preserving semantic styles instead of hard-coding visual formatting.
6. Render or otherwise verify page flow, headings, numbering, tables, links, and conversion fidelity.

Memory Manipulation

High

• Category: Memory Poisoning
• Confidence: 85% confidence

Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md

1. Clarify the target format, document count, style guide, required sections, protected content, tracked changes needs, and acceptable tooling.
2. Inspect headings, styles, numbering definitions, tables, fields, hyperlinks, images, footnotes, and section breaks before editing.
3. Choose the safest repair path: Word UI steps, python-docx, Pandoc, LibreOffice conversion, XML-level inspection, or manual style normalization.
4. Plan find-and-replace rules with examples, exclusions, backup strategy, and a dry-run report when batch changes are involved.
5. Apply or describe repairs in small reversible stages, preserving semantic styles instead of hard-coding visual formatting.
6. Render or otherwise verify page flow, headings, numbering, tables, links, and conversion fidelity.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill description contains broad trigger terms such as 'formatting', 'styles', and 'find replace' that can match many ordinary requests outside the narrow DOCX-repair use case. Overly broad routing can cause the agent to invoke this skill in unintended contexts, increasing the chance of inappropriate tool suggestions or unnecessary document-handling guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The trigger keyword list includes ambiguous everyday terms like 'formatting', 'styles', 'find replace', 'numbering', and 'tables' without requiring Word/DOCX context. This can lead to accidental invocation on unrelated tasks, which is a prompt-routing weakness because the skill may steer the model into irrelevant or riskier document-editing workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The trigger sentence is overly broad and begins with a generic phrase ('Help me'), which can cause the skill to activate for many unrelated requests. In an agent system, ambiguous activation increases the chance of misrouting user queries, inappropriate tool/skill selection, and prompt-surface expansion where unrelated content is handled under this skill's instructions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 83% confidence

Finding

This README is a Chinese-language user guide, but the applicable audience description is written in English on L11. That creates an implicit language/locale inconsistency in user-facing instructions without offering a user language choice or documenting why mixed-language output is required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.