Back to skill

Security audit

田伯光股票分析

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese stock-analysis report skill with Feishu document output and visible branding, not a hidden or destructive skill.

Install only if you are comfortable with reports being generated in Chinese, using the visible '田伯光' branding, and being written to Feishu. Treat the financial output as informational, verify sources independently, and do not rely on it as personalized investment advice.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:8
Finding

Mandatory Persona Branding and Attribution Injected into Generated Reports

Content
View full analysis
**出品:** 田伯光 ``` `SKILL.md:105-112`: ```markdown 2. **18维度深度分析** - 每维度核心数据 + 田伯光解读 3. **赚钱能力评估** - β属性、α属性、催化剂清单、赔率计算 4. **交易节奏指引** - 入场策略、持仓管理、出场策略 5. **机构评级 vs 田伯光评级** - 机构评级汇总、双重视角、差异分析 6. **新闻来源追踪** - 多源信息汇总、信息验证表 7. **特别关注点深度剖析** - 5大关注点深度分析 8. **关键跟踪指标** - 指标表格(观察频率/当前状态/关注阈值/信号含义) 9. **田伯光结语** - 一句话总结、投资者版操作建议、交易员版操作建议、风险提示 ``` `SKILL.md:220`: ```markdown - 主观判断必须以"田伯光解读/判断"形式明确标注 ``` `references/report-structure.md:57-61`: ```markdown **田伯光解读** - **估值视角:** xxxxx - **交易视角:** xxxxx - **关键阈值:** xxxxx ``` `references/report-structure.md:166-191`: ```markdown ## 第五部分:机构评级 vs 田伯光评级 ### 标准格式 ```markdown ## 第五部分:机构评级 vs 田伯光评级 ### 机构评级汇总 | 券商 | 评级 | 目标价 | 核心逻辑 | 日期 | |------|------|--------|----------|------| | XXX证券 | 买入 | XX元 | xxxxx | XX-XX | | XXX证券 | 增持 | XX元 | xxxxx | XX-XX | ### 田伯光双重视角 | 视角 | 评级 | 核心逻辑 | |------|------|----------| | **投资者视角** | 买入 | xxxxx | | **交易员视角** | 积极 | xxxxx | ### 差异分析 - **共识:** xxxxx - **分歧:** xxxxx - **田伯光判断:** xxxxx ``` `references/report-structure.md:263-280`: ```markdown ## 第九部分:田伯光结语 ### 标准格式 ```markdown ## 第九部分:田伯光结语 ### 一句话总结 XXXXX。 ### 投资者版操作建议 XXXXX。 ### 交易员版操作建议 XXXXX。 ``` ### Technical Analysis The Skill requires the Agent to adopt and repeatedly reproduce a named persona in stock-analysis reports. The branding is not confined to optional metadata: it is embedded in mandatory report headings, subjective analytical labels, rating comparisons, and the fin ...[truncated 2658 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description and core instructions are written to require Chinese output and use Chinese command formats such as "分析股票", with no indication that users may choose another language or locale. This creates a language/locale policy issue because the skill appears to enforce a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing instructions and examples exclusively in Chinese, and nowhere indicates that language selection is optional or configurable. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate that other languages are supported or that the language choice is optional. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill file is written only in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.