Security audit

message-chunker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward message-splitting helper with no executable code, credential handling, hidden persistence, or unrelated behavior.

Before installing, confirm you want the agent to split long replies into multiple outbound messages automatically, especially in channels where repeated messages, ordering, or duplicate retries matter. Consider tightening the triggers or adding confirmation for send-failure retries if you use it in public or high-volume messaging channels.

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The skill documentation is presented in Chinese with no indication that other languages are supported or that the skill is intended only for a Chinese-speaking or region-specific audience. This can violate language/locale policy because it imposes a specific language without user opt-in.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The description says the skill automatically activates whenever there is a need to send long messages such as reports, plans, or logs, which are very common content types and not a precise invocation scope. Without explicit constraints or negative examples, this broad wording could cause unintended activation in ordinary messaging scenarios.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The skill metadata and documentation are written entirely in Chinese and present the tool as operating in that language without offering a language choice or stating that it is region-specific. This can violate language/locale policy when users have not opted into Chinese-language behavior.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger list includes broad, underspecified conditions such as "multipleSections" and "sendFailure" without defining how these are detected or when the skill should not activate. In a manifest file, this lack of specificity can lead to inconsistent or overly broad activation behavior.

Static analysis

No suspicious patterns detected.