Security audit

Jike Hot Cn

Security checks for vulnerabilities and agentic risk

Overview

This skill appears low-risk to the system but should be reviewed because it presents itself as a live Jike hot-topic monitor while only returning fixed mock posts.

Install only if you understand this is currently a demo/mock Jike hot-topic formatter, not a real live monitor. The main concern is misleading functionality rather than unsafe system access.

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 (4)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 92% confidence
Finding: The description presents this skill as a Jike hot topics monitor/fetcher that gets trending posts, circle discussions, and user highlights. However, the code only defines a static in-memory list of mock posts and formats or serializes that list. There is no network access, API call, scraping, authentication, polling, or other mechanism to retrieve real Jike content. The primary behavior is demo/mock output generation rather than actual hot-topic monitoring, so the declared description materially overstates the real functionality.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger list includes broad terms such as “即刻” and “圈子,” which may cause the skill to activate on ordinary conversation unrelated to the intended Jike use case. Overbroad activation can lead to unintended invocation, confusing behavior, and possible exposure of user prompts or context to a skill when the user did not intend to use it.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The manifest includes locale-specific tags such as "china" and "chinese", which suggests the skill may be oriented toward a specific language or region. The file does not explicitly state that this locale constraint is optional or justified as a region-specific tool, so it may conflict with the policy against forcing a language/locale without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This code emits a fixed Chinese header string in its default output, and the surrounding comments/docstrings are also Chinese-first. The file provides no opt-in, language selection, or documented justification for restricting output language, which can violate language/locale policy expectations.
Content: No source excerpt is available for this finding.