ClawHub
Back to skill

Security audit

Local Festivals

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local festival guidance skill with some broad consumer-style wording, but no hidden code, privileges, persistence, or unsafe behavior.

Users should treat this as a local event discovery guide, not just a cultural reference. Review any reservation, ticketing, queue, or promotion information before acting on it, especially if it comes from third-party or community sources.

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 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 (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill provides non-heritage event lists, temple fair/lantern fair guides, and traditional festival cultural education. However, the documented filters and return fields focus on distance-based venue discovery, popularity rankings, pricing tiers, reservations, ticket numbers, parking, navigation, user photo galleries, and shop-visit notes, which align more with a local commerce/POI recommendation tool than a festivals information skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The example trigger phrases are overly generic, such as asking how to use the skill for a 'specific scenario task' or asking about 'core features' and 'latest玩法/优惠信息'. Broad invocation language can cause accidental activation in ordinary conversation, leading the agent to route unrelated user requests into this skill and potentially expose irrelevant third-party content or produce inappropriate actions based on mistaken skill selection.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description limits scope to non-heritage activities, temple/lantern fair guides, and traditional festival education. In contrast, the document header '民俗节庆' and the example requests for latest '玩法/优惠信息' suggest a broader consumer-exploration and promotions use case, which conflicts with the declared cultural-information focus.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.