Back to skill

Security audit

Title Replier

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple reply formatter that adds Chinese title labels and stores only title-use history locally, with no network, credential, dependency, or privilege behavior found.

Install this only if you want assistant replies decorated with Chinese title labels. Avoid enabling it in workflows that require exact formatting, and be aware it keeps a local history.json of used titles so titles do not repeat.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description is written to impose Chinese-language behavior as part of the skill's presentation without indicating user consent or localization controls. In practice, this can cause unwanted language switching, reduced usability, and instruction conflicts when the user expects responses in another language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states it will automatically prepend titles to replies without any activation constraints, which creates an always-on behavioral modification. Broad automatic triggering can unexpectedly alter all assistant outputs, interfere with higher-priority instructions, and affect contexts where extra formatting or persona-like labeling is inappropriate or unsafe.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file description and behavior are entirely specified in Chinese, indicating the skill is designed to produce Chinese honorific titles and replies. There is no natural-language indication that users can opt into another language or that the Chinese-only behavior is required for a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The package description states the skill adds titles to assistant replies using Chinese text, which implies a fixed language behavior. There is no indication that users can choose their preferred language or opt in to Chinese-only output, which violates the language/locale policy requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The value "代码搬运工" indicates a Chinese-language label/history entry, while the file provides no indication that language choice is user-selectable or that this locale constraint is justified. The policy requires avoiding forced language or locale choices unless users can opt in or the restriction is explicitly documented.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest says the skill adds random non-repeating titles to assistant replies, which suggests transient formatting behavior. The code also creates and updates a local history.json file to persist title usage across runs, adding stateful file I/O behavior not reflected in the description.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

Beyond generating decorated replies, the code implements a command-line interface that lists all titles, prints usage history, and resets persisted history. Those management capabilities are not necessary for the stated purpose of adding fun, personalized titles to replies and expand the skill's operational surface.

Content

No source excerpt is available for this finding.