ClawHub
Back to skill

Security audit

Kaomoji Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small kaomoji picker that can also update its own local kaomoji list, with no evidence of network access, credential use, or hidden system changes.

Install only if you are comfortable with a kaomoji helper that can update its own bundled JSON list when the save command is invoked. Review added entries if multiple users or agents can modify the skill folder, since saved kaomoji text may later be selected in conversations.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The skill is presented as a selector but also persists and updates local data through a save utility, effectively acting as a small database maintenance tool. This hidden state-changing behavior is risky because users or orchestrators may treat it as read-only while it can modify files and introduce persistent, potentially untrusted content.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The skill is presented as a selector but also persists and updates local data through a save utility, effectively acting as a small database maintenance tool. This hidden state-changing behavior is risky because users or orchestrators may treat it as read-only while it can modify files and introduce persistent, potentially untrusted content.

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill advertises executable scripts that read and write local data, but the manifest declares no explicit tool scope or permissions. This creates a least-privilege and transparency problem: an agent or reviewer cannot easily tell that the skill modifies local files, increasing the chance of unintended data access or persistence.

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The manifest frames the skill as a selector that chooses kaomoji from context tags, which implies lookup/retrieval behavior. This code implements create/update persistence into kaomojis.json, materially expanding the behavior from selection to maintaining the underlying dataset.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The entry "Ciallo～(∠・ω< )⌒☆" is presented as a general-purpose "daily greeting" and "first interaction" usage without indicating that this non-English expression is optional, user-selected, or limited to a specific locale. This can conflict with language/locale policy expectations when a skill may insert greetings in a language the user did not choose.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
This code file contains natural-language strings such as the docstring and printed output entirely in Chinese. Under the policy rule for language or locale constraints, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.