Back to skill

Security audit

SKILL1

Security checks for vulnerabilities and agentic risk

Overview

This local file organizer is mostly coherent, but it falsely says it does not read file contents even though duplicate detection hashes file contents.

Install only if you are comfortable running a local file-management script on explicitly chosen directories. Use dry-run first, inspect the planned moves/deletions, and avoid duplicate scans on sensitive folders unless you accept that the script will read file bytes locally to compute hashes.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README makes a materially inaccurate security/privacy claim: duplicate detection by SHA-256 requires reading file contents, so stating that the tool 'does not read file content' can mislead users about how sensitive files are handled. In a file-management tool, incorrect claims about data access can cause users to run the tool on confidential directories under false assumptions, creating trust and privacy risk even if no network exfiltration occurs.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code presents its top-level description entirely in Chinese and continues to use Chinese-only user-facing CLI messages throughout the file. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The title includes a Chinese-only skill name component ("文件整理助手") and the rest of the README is written entirely in Chinese, with no indication that users may choose another language. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.