Back to skill

Security audit

文件

Security checks for vulnerabilities and agentic risk

Overview

This file-organizer skill is not clearly malicious, but it requests broad write and command-execution authority for file cleanup tasks without enough safeguards.

Install only if you are comfortable granting an agent broad local file modification and command-execution capability. Use it only on backed-up, non-sensitive folders, insist on a preview plan before any move/delete action, avoid administrator/root execution, and do not provide API keys unless the skill clearly explains what data will be sent externally.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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 (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:16
Finding

Excessive Command Execution Privileges and Unsafe Elevation Guidance

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (6)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises file classification and duplicate cleanup but does not prominently warn that these operations can move, rename, or remove user data. In a file-management context, lack of a destructive-operation warning is especially dangerous because users may assume a safe preview while the skill could perform irreversible changes.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

A file organizer generally needs filesystem read/write operations, but unrestricted or loosely described system command execution greatly expands the attack surface. If an agent follows these instructions, ambiguous user input could be transformed into shell actions that modify the system, delete data, or run arbitrary programs beyond the stated purpose of organizing files.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance is broad enough to match many unrelated requests, increasing the likelihood that the skill activates outside its intended context. In a skill with write and exec capabilities, over-broad triggering is dangerous because it can cause the agent to apply high-impact operations to requests that did not clearly ask for file reorganization.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill claims to organize local files, yet it introduces external API usage and API key handling without a clear necessity. This creates unnecessary data-exposure risk because file names, paths, contents, or metadata could be transmitted off-host, and it also encourages handling secrets in a workflow that should not need them.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The example trigger phrases are extremely short and do not communicate what actions may be taken, whether files will be moved, renamed, or deleted, or whether duplicate cleanup is enabled. In context, this makes accidental destructive execution more likely because users may invoke the skill casually without understanding the consequences.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is presented as a local file organizer, but the documentation later broadens its scope to API integration and command execution. This mismatch is dangerous because users or agents may grant the skill permissions appropriate for harmless file sorting while it is actually positioned to invoke external services and execute system-level actions, increasing the chance of over-privileged or unintended behavior.

Content

No source excerpt is available for this finding.