Security audit

File Inbox

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local file inbox skill, but it needs review because it can move files by default and stores unsanitized file metadata in a persistent index that agents are told to read.

Review this skill before installing. Use it only in workspaces where moving files into an inbox is expected, prefer --copy when preserving originals matters, and treat inbox/INDEX.md as untrusted data if filenames, sender names, tags, or notes may come from other people.

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/register_file.py:134
Finding: Persistent Markdown Injection in the Inbox Index
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: scripts/register_file.py:184
Finding: Directory Paths Are Accepted by a File-Only Registration Operation
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 92% confidence
Finding: The declared description presents a general bidirectional file management system used to save user files, generate/send files, and find/list/search previously exchanged files. The supplied code chunk does not implement those core behaviors. Instead, it is a narrow reporting script that inspects an existing inbox directory, parses metadata and an index markdown table, measures directory sizes, and prints summary statistics such as totals, file types, tags, and recent activity. While this is related to the same inbox resource, its primary purpose is analytics/status display, not file management or retrieval. Therefore the description materially overstates and mischaracterizes what this code chunk actually does.
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.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The script performs a move operation by default, which removes the file from its original location and is a user-data-affecting action. Although the usage text mentions 'move' as the default, there is no runtime confirmation prompt or explicit warning immediately before the operation in code.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.