Back to skill

Security audit

深蓝AI分析师

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed client for a public financial-news API, with expected network use and no evidence of hidden local access, persistence, credential use, or destructive behavior.

Install only if you are comfortable with the agent making HTTPS requests to Shenlan News for financial article analysis, AI editor feeds, and TTS. Treat the outputs as informational, not investment advice, and ask explicitly before generating TTS audio because it may return a remote audio link.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

L003 将触发条件描述为“当用户需要对财经内容进行AI分析…或想查看…或需要将文章转为语音播报时使用”,覆盖面很广,但没有明确的触发短语、边界条件或排除情形。这样的描述容易匹配到日常泛化表达,例如泛泛的‘帮我分析一下’或‘读出来’,从而造成非预期调用。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill encourages sending article or user-provided content to an external API but does not disclose that this constitutes third-party processing. If users provide non-public, proprietary, or personal text for analysis, the skill may transmit sensitive data off-platform without informed consent or minimization.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

L157 使用“当用户问‘市场情绪怎么样’时”作为调用条件,但未说明是指A股、港股、美股、加密市场,还是仅限深蓝站内近况数据。这种自然语言触发条件缺乏范围限定,容易在用户泛问市场情况时被不恰当地激活。

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

L166 的“当用户问‘某某股票的舆情分析’时”没有说明仅基于站内文章搜索结果,也未说明代码、市场或时间范围要求。该触发表述可能覆盖大量常见投资问法,导致在缺少必要上下文时仍被触发。

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The TTS workflow explicitly says to trigger generation when audio is absent, but it does not warn that this may cause remote processing and creation of a persistent audio resource URL. Users may not realize their content is being transformed, stored, or made retrievable through a generated link on a third-party service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

该 API 参考文档标题及全文均以中文呈现,但没有说明这是面向特定中文用户群体的区域性文档,也没有提供语言选择或英文替代说明。按规则,未给出用户语言/区域选择的强制语言呈现可构成自然语言层面的语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code includes user-facing natural-language text primarily in Chinese, including the module description and command help, with no opt-in or alternative locale selection. Under the policy, forcing a specific language without user choice is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.