Security audit

DOCX Compare

Security checks for vulnerabilities and agentic risk

Overview

The skill appears intended for DOCX duplicate checking, but its file handling and DOCX parsing have review-worthy risks for local file loss or resource exhaustion.

Install only if you trust the DOCX files you will process and can run it in a controlled working/output directory. Avoid pointing output at directories containing important files, especially files named like __tmp_<document>.docx, and be cautious with large or untrusted DOCX files.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/compare_docx.py:614
Finding: Predictable Temporary Files Permit File Overwrite and Deletion
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/compare_docx.py:166
Finding: Unbounded DOCX Archive Decompression Enables Memory Exhaustion
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (2)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill documentation declares no explicit tool scope or permission boundaries, yet the described functionality clearly writes output files such as highlighted DOCX documents and text reports. Without an explicit permissions/allowed-tools declaration, an agent may invoke file-writing behavior with broader-than-expected filesystem access, increasing the risk of unintended overwrites or writing to sensitive locations if parameters are user-controlled.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The module docstring, usage text, and all user-facing descriptions are written only in Chinese, and later CLI/help messages are likewise Chinese-only. This imposes a specific language/locale on users without offering opt-in or documenting a justified region-specific limitation, which matches the language-policy violation criteria.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.