Security audit

地震信息查询

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently queries public earthquake data from CENC and does not show hidden, destructive, credential-seeking, or persistent behavior.

Install only if you are comfortable with the skill contacting CENC when earthquake information is requested. The publisher should ideally narrow the invocation rules and declare the network endpoint explicitly, but the inspected artifacts do not show unsafe local access or persistence.

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 (5)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.
md
entry: scripts/main.js

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill declares an entry script and the static analysis indicates network capability, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. That creates a least-privilege and transparency gap: reviewers and the hosting agent cannot clearly constrain or audit what external access the skill is expected to use, increasing the risk of unintended or overly broad outbound requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger section uses broad keyword-based activation for terms like 地震, 震级, 震源, and related phrases without meaningful exclusion rules. This can cause the skill to activate on general conversation or ambiguous references, leading to unnecessary network queries and incorrect skill routing rather than a direct code-execution flaw.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The agent prompt instructs invocation whenever the user asks about terms such as 地震, 震动, or 震级, which is overly permissive and may trigger the skill for loosely related discussion. In context, this mainly increases the chance of misfires, unnecessary external requests, and degraded agent behavior, not severe compromise.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This JavaScript file uses Chinese exclusively in docstrings, inline comments, and thrown/returned error messages. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.