ClawHub
Back to skill

Security audit

gettangemperors

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently performs a fixed local read-only API request for Tang emperor data and shows no hidden, destructive, persistent, or credential-seeking behavior.

Install this only if you intend Codex to query a local backend at 127.0.0.1:8080 for this data. Confirm that service is yours or trusted, since the skill will send a GET request to that localhost endpoint when used.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill performs network access to a local HTTP service but does not declare any tool scope or allowed-tools constraints. That omission weakens policy enforcement and reviewability, making it easier for an agent to invoke network-capable behavior without explicit authorization boundaries, especially against localhost services that may expose sensitive internal APIs.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger text is broad enough to cause invocation whenever users mention Tang emperors or related Chinese phrases, even when a local API call is unnecessary. Over-broad activation can increase the chance of unintended localhost requests and surprise network behavior, though the impact is limited here because the endpoint and use case are narrowly defined.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The script emits user-facing text in Chinese (for example, the heading and emperor label) with no opt-in, fallback, or configuration for other languages. This is a natural-language policy concern because it forces a specific language on users rather than allowing a language choice.

Static analysis

No suspicious patterns detected.