Security audit

Echo Test

Security checks for vulnerabilities and agentic risk

Overview

This is a small echo-and-time test skill with broad activation wording but no evidence of hidden access, network use, persistence, or destructive behavior.

Installers should understand that this skill is written for Chinese-language use and has very broad invocation wording, so it may activate on ordinary conversation unless the host platform scopes it more tightly. It appears low risk because it only echoes input and reports the current time.

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

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 (3)

Vague Triggers

Medium

Confidence: 97% confidence
Finding: The trigger text is effectively 'say anything,' which makes the skill eligible to activate on ordinary conversation with no clear scoping. Overly broad activation increases the chance of accidental invocation, routing unrelated user input into this skill and creating confusion, privacy exposure, or interference with intended workflows.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The skill metadata and instructions are entirely written in Chinese, with no indication that language selection is optional or that the skill is intended only for a Chinese-speaking context. This may reflect a language/locale constraint without user opt-in or documented justification.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: The docstring, comments, test input, and returned user-facing strings are all written in Chinese, and the skill provides no indication that language is selectable or that the locale is intentionally restricted. This can violate the language/locale policy because the skill effectively assumes a specific language without user opt-in.

Static analysis

No suspicious patterns detected.