Security audit

Json Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local JSON utility, but users should know some operations overwrite or create files unless an output path is used.

Install only if you are comfortable with a local script reading and writing JSON files you point it at. For important data, pass --output or keep a backup because some operations modify the original file by default.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Note

Location: scripts/json_tool.py:121
Finding: Unpinned Third-Party Dependency Installation Guidance
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 (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 82% confidence
Finding: The skill documentation advertises running a local Python script that can format, minify, convert, and sort JSON, and the static analyzer detected file-write capability, but the manifest declares no explicit tool scope such as permissions or allowed-tools. That creates an authorization and transparency gap: consumers of the skill cannot tell up front that it may modify or create files, especially during conversions or formatting operations that commonly write output. In this context the capability is plausibly legitimate, but undeclared write access still increases risk if the implementation writes unexpected paths or overwrites user data.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The tool defaults to writing formatted, minified, or sorted JSON back to the original input file when no --output path is supplied. This creates an unsafe destructive side effect: a user or calling agent expecting a read-only transformation can unintentionally overwrite source data, potentially causing data loss or corruption of important configuration files.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The conversion paths create .yaml or .csv files on disk, but the skill only states it can 'transform JSON data' and does not disclose that conversion produces new files. This is a file-writing side effect that lacks an upfront user warning in the code's visible descriptions or CLI help.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.