Back to skill

Security audit

global-biblio-base

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because scanners report a gateway authentication secret in the package and concerns about account identity and undisclosed sharing of research queries; scan coverage was partial.

Consider the reported packaged secret and the possibility that research terms and account activity may be shared externally or associated with a configured email. The scan was partial: one file was only partly inspected and a static analysis step was degraded, so the evidence is incomplete.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
config.json
Finding

Gateway authentication secret distributed in the Skill package

Content
View full analysis

Impact

Exposure of the gateway's shared authentication credential removes that authentication barrier for package recipients. The instructions additionally state that GATEWAY_SECRET signs consume tokens, increasing the importance of rotating and separating this key. Actual token-forgery feasibility, remote credential validity, and cross-account access were not verified because the gateway implementation is absent and no network requests were performed.

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (8)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 385)May include surrounding context.

md
| **单次查询条数**| PageSize 20-1000,建议 ≤100 以保证速度|
| **翻页上限**| 无硬限制,但建议不超过 50 页(共 1000 条)/ No hard limit, but ≤50 pages recommended |
| **请求频率**| 有频率限制(未公开数值),触发 429 时自动等待重试|
| **Token 有效期**| Access Token 30 秒,Refresh Token 2 小时(以下游 API 返回为准)。系统自动管理刷新|
| **下载链接有效期**| 约 10 分钟(以下游返回为准),过期需重新调用下载接口|
| **依赖**| 完全依赖 SmartLib API 和网络连接,离线不可用|

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 1037)May include surrounding context.

md
|------|------|
| **检索不到想要的论文怎么办?** | 1. 去掉过滤条件扩大范围 2. 尝试上位词 3. 用英文关键词在接口4再试 4. 用 `U=` 替代 `T=` |
| **全文下载失败怎么办?** | 仅中文期刊支持全文下载。下载 URL 约 10 分钟有效(以下游返回为准),过期需重新调用。英文文献自动走多渠道下载策略获取 OA 版本。 |
| **Token 多久过期?** | Access Token 约 30 秒,Refresh Token 约 2 小时(以 API 返回为准)。系统自动管理刷新,用户无感知。 |
| **英文文献能不能下全文?** | 本技能集成十级多渠道下载策略(ArXiv → Unpaywall → CORE → OpenAlex 等),Gold/Green/Hybrid OA 论文成功率 >85%。付费墙内论文无法获取。 |
| **配额耗尽后还能用吗?** | 不能。试用额度耗尽后 Gateway 返回 429 拒绝所有检索请求,并自动弹出套餐选择;如需更高额度,回复套餐数字或说「升级 / 充值」即可(企业 / 机构定制联系 vipsmart@vipslib.com)。 |
| **计费 token(consume_token)是一次性的吗?** | **是的,务必注意。** 每次 `/consume` 返回的 `consume_token` **仅能使用一次**且 **约 60 秒过期**。获取后要立刻调用 `/search` 或 `/download`,不要缓存或复用;过期/已用需重新 `/consume`。这与 SmartLib 云端 Access/Refresh Token(约 30s/2h,以 API 返回为准,系统自动刷新)是两回事。 |

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 1069)May include surrounding context.

md
- 检索策略遵循三级分级体系:默认平衡策略,综述自动切换宽检索,引用自动切换窄检索
- 检索→评估→调整→再检索是核心工作流
- Access Token 有效期约 30 秒,Refresh Token 约 2 小时(以 API 返回为准),系统自动管理刷新
- 全球文献检索(接口4)仅提供元数据,部分无全文
- 中文期刊(接口1-3)支持全文下载,是核心优势,应优先推荐
- PageSize 建议不超过 100

The search workflow lacks a privacy notice about sending users' research queries to external services.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

These examples direct the assistant to search automatically and retrieve papers through external providers. Although the README lists SmartLib and its gateway as dependencies, it does not disclose that users' search terms or research topics will be transmitted outside the conversation; those topics may contain confidential research information.

Content

No source excerpt is available for this finding.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding

Shadow Command Trigger: description clause '"写文献综述""找几篇引用支撑论点"。英文:"find papers" "search literature" "write literature review" "find supporting citations"。

调用前必须先用 /consume 获取 consume_token,再凭 token 调 /search(每次计费接口调用都需一次 /consume)。' conflicts with built-in command 'search'

Content

No source excerpt is available for this finding.

The credential workflow reuses a configured email despite explicitly requiring a user-supplied email on every invocation.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The workflow directs the agent to proceed using an already configured email, contradicting the explicit requirement to obtain the current user's email on every invocation. On shared or reused installations, this ambiguity could associate searches with another person's account, expose account quota information, or consume their purchased quota.

Content

No source excerpt is available for this finding.

Mandatory web-based keyword expansion lacks a disclosure that user research terms are sent to external search providers.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill mandates external web searches for keyword expansion and translation, sending research terms to additional providers beyond the advertised literature service without an explicit disclosure or opt-out. For unpublished research, patent development, or sensitive medical topics, these terms can reveal confidential interests even if no full document is transmitted.

Content

No source excerpt is available for this finding.

The template mandates Chinese-language payment output without offering a language choice.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The instructions require generating payment HTML strictly from this template and prohibit changing anything except placeholders, thereby preventing translation of its Chinese interface text. Line L017 also explicitly requires a Chinese plan name; no user language opt-in or justification for making Chinese mandatory is provided.

Content

No source excerpt is available for this finding.