Back to skill

Security audit

jike-digest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Jike topic digest helper with disclosed fetching, filtering, and local Markdown output behavior, though users should review its output directory cleanup step.

Before installing, set JIKE_DIGEST_BASE_DIR to a directory you are comfortable using for generated digests, and check the existing-output cleanup behavior so it does not remove files you meant to keep. Also make sure you trust and understand the separate autocli Jike command, since this skill relies on it to fetch topic content.

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
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 (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

声明描述的是一个完整的“即刻日报/摘要”流程:抓取 topic 内容、筛选高价值帖子、生成分析性文本并输出 Markdown。实际代码只是一个辅助过滤脚本,功能局限于读取已有 JSON 数据并依据 time 字段保留最近若干小时的帖子。它没有任何网络抓取逻辑,没有 limit 50 的控制,没有内容质量判断,也没有摘要或文档生成功能。虽然“保留最近 24 小时内容”与声明中的一部分相符,但整体主用途明显比声明窄得多,且输出形式也不同,因此属于明显不匹配。

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill describes reading from and writing to the local filesystem, including creating output directories and writing Markdown files, but it declares no explicit tool scope or permissions. In an agent environment, missing scope declarations can cause overbroad execution privileges or prevent operators from understanding that the skill performs local file operations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The workflow instructs the agent to clear existing topic-related files if the destination directory already exists, but provides no confirmation, backup, or narrowly defined deletion procedure. This can lead to accidental data loss, especially because the base directory is configurable and file cleanup behavior is underspecified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction mandates using Simplified Chinese for the generated document, which imposes a language choice regardless of user preference. The file does not indicate that this is optional, user-selected, or justified by a region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring, CLI description, help text, and runtime messages are written exclusively in Chinese, which imposes a specific language on users. Under the policy rule, locale or language constraints should either be optional, user-selectable, or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file’s headings, instructions, and output template are entirely in Chinese, which can amount to a language/locale constraint embedded in the skill artifact. There is no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-language or region-specific use case.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

脚本整体和文档允许通过 --hours 自定义时间窗口,但 L086 的日志固定写成“24h 内”,会在传入 48 等其他值时与真实行为相矛盾。虽然不改变核心功能,但这是注释/输出文本对实际执行语义的明确误导。

Content

No source excerpt is available for this finding.