Back to skill

Security audit

Filesystem Management

Security checks for vulnerabilities and agentic risk

Overview

This filesystem skill requests broad local file access, but its documented behavior is coherent with file listing, searching, analysis, and user-directed copying.

Install only if you want an agent-facing tool with read-write access to local files. Prefer dry runs before copy operations, verify destination paths carefully, and be cautious with --overwrite or broad recursive searches over private directories.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This markdown file documents a command that performs filesystem writes and allows --overwrite, which can affect user data. Although it mentions safety checks and dry-run support elsewhere, this command reference section does not explicitly warn that running copy without --dry-run or with --overwrite may modify existing files.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The example shows a live copy operation using --preserve but does not indicate that it will write files immediately or recommend a dry run first. For markdown files, user-facing descriptions should warn about behaviors that can affect user data or system state.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This JSON manifest is in scope for vague-trigger checks. The description 'Advanced filesystem operations - listing, searching, batch processing, and analysis' is broad and does not specify when the skill should or should not be invoked, which could contribute to overly loose activation in systems that rely on manifest text for routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest keywords include very broad terms such as 'files', 'directories', 'search', and 'automation'. In trigger- or routing-based systems, such generic terms can cause accidental invocation because they overlap with everyday language and lack negative examples or contextual constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.