Security audit

url编解码

Security checks for vulnerabilities and agentic risk

Overview

This is a local URL encoding and decoding utility with limited, disclosed behavior and no evidence of data exfiltration, persistence, or destructive actions.

This skill is reasonable to install for local URL encoding and decoding. Users should be aware that ambiguous text may be auto-encoded or auto-decoded incorrectly, and non-Chinese users may need to ask their agent to respond in their preferred language.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The README claims the skill will 'intelligently' auto-detect user intent without requiring explicit mode selection. In an agent setting, ambiguous auto-detection can cause the skill to activate on unintended inputs or choose encode vs. decode incorrectly, which may alter user data, mis-handle URLs, or produce unsafe downstream transformations. The issue is not code execution, but unreliable intent inference in a transformation tool can still create security and integrity problems when used inside larger workflows.

Lp3

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases are generic and likely to match ordinary conversation about encoding/decoding, which can cause the skill to activate outside a narrowly intended context. Over-broad activation increases the chance of unintended tool use, confusing responses, or interception of user requests that should have been handled by another skill or the base assistant.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The instructional content, workflow, error messages, and examples are written entirely in Chinese and direct the assistant to respond with fixed Chinese phrases. This imposes a language choice without offering the user a locale or language option, which is a natural-language policy concern under the language/locale rule.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The function documentation and user-facing return messages are written only in Chinese, which indicates the skill is designed to communicate in a single language without offering a user choice. The policy for this category requires flagging language or locale constraints unless the skill explicitly provides opt-in or justification.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The README presents the skill entirely in Chinese and all user interaction examples assume Chinese-language usage, without offering a language choice or stating that the skill is intentionally Chinese-only. This can violate language or locale policy when a skill implicitly forces one language without user opt-in.

Static analysis

No suspicious patterns detected.