Back to skill

Security audit

sci-journal-search

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed SCI journal lookup helper with expected network/browser use and no hidden persistence, credential access, or destructive behavior.

Install this only if you are comfortable with it querying external journal sites and, when using --letpub, letting the agent open LetPub in a browser and close/stop the browser session afterward. The skill would benefit from clearer bilingual documentation, but the inspected behavior is purpose-aligned.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description, headings, examples, and operational instructions are entirely in Chinese, with no indication that users may choose another language or locale. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file’s docstring and command descriptions are exclusively in Chinese, and there is no indication that users can select another language or locale. 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.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The module docstring and CLI description present this as an SCI journal query tool that queries XinRui by default and LetPub optionally. However, the LetPub path is implemented by spawning another Python script via subprocess rather than by direct querying logic, which introduces process-execution capability not justified by the stated purpose of a lookup tool.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/query.py (reported line 158)May include surrounding context.

python
import subprocess
            # 使用扩展后的全称查询 LetPub,而不是原始简称
            letpub_keyword = keyword if keyword else args.keyword
            result = subprocess.run(
                [sys.executable, str(letpub_script), letpub_keyword],
                capture_output=True,
                text=True

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

该技能说明全文均以中文呈现,未见提供其他语言选项、用户语言偏好说明,或明确声明该技能仅面向特定中文用户群体。根据语言/locale 政策,若技能实际上强制单一语言而无用户 opt-in,属于自然语言层面的潜在政策问题。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language description at L004 is written only in Chinese, which can indicate a language-specific constraint without offering user choice or documenting that the skill is intended only for a Chinese-speaking context. Under the policy rule, locale or language restrictions should be opt-in or clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The natural-language description is presented only in Chinese, which can impose a language constraint on users without opt-in or explanation. Under the language/locale policy, this is a potential issue unless the skill clearly documents that it is intentionally region- or language-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This reference file presents all instructional and descriptive content exclusively in Chinese and does not indicate any optional locale or audience constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This Python file contains only Chinese-language natural-language strings for the docstring, usage guidance, status messages, and formatted output. That imposes a specific language choice on users without offering an alternative or opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.