ClawHub
Back to skill

Security audit

Office-Editor

Security checks for vulnerabilities and agentic risk

Overview

This skill helps create and edit Office files, and its file-writing behavior is disclosed, limited to that purpose, and avoids automatic installs or overwrites.

Install this if you want Codex to create or edit Office documents. Review generated files before sharing them, and be explicit about output filenames when working with important documents, because the skill is designed to write local .docx, .xlsx, and .pptx files.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
- Basic PowerPoint generation only: start with `{baseDir}/scripts/create_presentation.py`
- PowerPoint charts: read `{baseDir}/references/pptx_chart_guide.md` first

## Output Rules

- Always save to a concrete target filename. Do not leave changes only in memory.
- If the user does not provide a filename, use a clear default such as `report.docx`, `budget.xlsx`, or `deck.pptx`.
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest says to use this skill when the user mentions broad terms like "Office," "Word," "Excel," "PowerPoint," "spreadsheets," "presentations," or "document export." Several of these terms are common in everyday requests and the file provides no negative examples or tighter activation constraints, increasing the risk of unintended invocation.

Static analysis

No suspicious patterns detected.