Back to skill

Security audit

article-taster

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese article-analysis skill with some quality and hardening gaps, but I found no hidden, persistent, destructive, or data-exfiltrating behavior.

Reasonable to install for local Chinese article scoring, but treat the AI/originality results as heuristic opinions, not proof. Avoid running it as a shared service on arbitrary large submissions without input limits, pin dependencies before production use, and render generated Markdown with raw HTML and remote resource loading disabled.

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/report_generator.py:59
Finding

Unescaped User-Controlled Title Allows Markdown and HTML Content Injection

Content
View full analysis
Remediation
View remediation
str: value = value.replace("\r", " ").replace("\n", " ") value = re.sub(r"([\\`*_{}\[\]()#+.!|><-])", r"\\\1", value) return value[:200] safe_title = escape_markdown_text(str(report["title"])) md = f"- **Title**: {safe_title}\n" ``` ]]>

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/ai_detector.py:42
Finding

Unbounded Backtracking Regular Expressions Permit Denial of Service

Content
View full analysis
Remediation
View remediation
Dict: if len(content) > MAX_ARTICLE_CHARACTERS: raise ValueError("Article exceeds the permitted analysis size") # Continue with bounded analysis. ``` This guard should be combined with replacement of the backreference patterns because input limits alone do not guarantee predictable regex execution time. ]]>
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (24)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

声明描述的核心能力是文章质量鉴赏与内容属性检测(质量评估、AI味检测、原创性识别),但代码并未执行这些任务。实际代码仅通过预设关键词匹配和简单评分逻辑,对文章类型进行分类,并支持用 user_hint 覆盖自动结果。这不是对声明功能的支撑细节,而是一个 materially different primary purpose。因此描述与行为明显不符,应判定为 mismatch。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

声明描述包含三类核心能力:多维度文章质量评估、AI味检测、原创内容识别。代码只覆盖了其中一部分,即基于关键词、段落、句式、比喻、第一人称等浅层特征,对情感散文或小说进行多维度写作分析。它没有任何用于检测AI生成文本特征、判断“原创性”、比对外部内容、查重或相似度分析的逻辑,也没有访问相关资源。并且模块文档和实现都表明其主要用途是“情感散文与小说分析”,范围比声明中的泛化“文章品鉴师”更窄。因此描述对代码能力有明显夸大,属于描述与实际行为不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

声明描述强调的是通用文章质量评估,以及AI味检测、特定风格/低质味道检测和原创性识别。但代码并没有实现这些核心能力:没有AI文本检测逻辑、没有原创性/相似性比对、没有任何针对“大便味”的专门判定。相反,代码明显聚焦于小说场景,包含小说体裁检测、情节结构分析、人物塑造分析、叙事技巧分析、世界观构建,以及剧透风险分级和无剧透输出。这与“文章品鉴师”的泛化定位和其列出的关键能力存在实质性偏差,因此属于描述与行为不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

声明与代码部分重合在“多维度评估文章质量”和一定程度上的“原创性评估”,但核心描述中的“检测AI味/大便味”在代码中完全没有对应实现,也没有任何与AI生成痕迹、文风异常、套路化表达等相关的检测逻辑。代码的主功能更具体地偏向技术文章质量打分,而不是广义的文章品鉴师。因此描述对能力范围有明显夸大,属于描述与实际行为不一致。

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
81% confidence
Finding

The skill advertises executable components and optional LLM-backed analysis but does not declare any explicit tool scope or permissions. In agent environments, missing scope boundaries can allow broader-than-expected file reads or network access, increasing the chance of data exposure or unintended external calls when users supply sensitive article content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest-style header declares only '中文' under languages, which indicates a language constraint without any user opt-in, alternative locale, or documented regional justification. This is a natural-language policy concern because it forces a specific language/locale behavior rather than presenting it as a user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This Python file contains natural-language strings entirely in Chinese for the module description and later user-facing outputs, indicating the skill is designed to operate in a fixed language. Under the policy rule, forcing a specific language without user opt-in is a locale/language policy violation unless clearly justified as region-specific, which is not documented here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The confidence labels and explanatory analysis returned by the detector are emitted only in Chinese, which constrains downstream user interaction to a single language. Because the file does not provide a user choice or documented locale restriction, this is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The module title, description, and class docstring all specify behavior only in Chinese, and there is no indication that users may interact in other languages or that the locale restriction is intentional for a region-specific use case. 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

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code file contains user-facing natural-language strings entirely in Chinese, including the module description and command help/output text, but does not indicate that the skill is region-specific or provide an opt-in language choice. That creates a language/locale policy issue under the rule for forced language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

SQP-3 applies to all file types and covers language/locale policy violations. The module description, docstrings, and user-facing output strings indicate the skill is effectively fixed to Chinese, with no documented user opt-in or alternative locale handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This Python file contains user-facing natural-language content entirely in Chinese, including the generated markdown report headings, labels, and descriptions. Because the skill does not offer any language/locale selection or document that it is intentionally China/Chinese-specific, it creates a language policy concern by implicitly forcing one locale on all users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code file contains natural-language descriptions and user-facing recommendation text exclusively in Chinese, including module descriptions and verdict/advice strings. Under the policy, forcing a specific language without user opt-in or a documented region-specific justification is a language/locale policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language descriptions and output strings in Chinese, including the module description and analyzer class/docstrings, with no indication that the skill is intentionally region-specific or that users can opt into another language. Under the language/locale policy, forcing a specific language without user choice is a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The issue and strength messages generated by the analyzer are all hard-coded in Chinese and are likely surfaced to end users. Because the file does not provide an opt-in language selection or justify a Chinese-only scope, this conflicts with the stated policy on language/locale constraints.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
91% confidence
Finding

The dependency is specified with a lower bound only, which allows different installations to resolve to different versions over time. This weakens build reproducibility and can unintentionally introduce a vulnerable or incompatible release into the environment.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
jieba>=0.42.1
scikit-learn>=1.0.0
numpy>=1.21.0

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
96% confidence
Finding

scikit-learn is unpinned, so the installed version cannot be predicted or audited reliably. Because the package has known historical advisories, leaving it unconstrained increases the risk that a vulnerable version could be installed in some environments.

Content

Scanner excerpt · requirements.txt (reported line 2)May include surrounding context.

text
jieba>=0.42.1
scikit-learn>=1.0.0
numpy>=1.21.0

Unverifiable Dependency: scikit-learn has 6 known advisory(ies) (CVE-2020-13092 (scikit-learn Deserialization of Untrusted Data); CVE-2024-5206 (scikit-learn sensitive data leakage vulnerability); CVE-2020-28975 (scikit-learn Denial of Service) +3 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
88% confidence
Finding

The manifest does not pin scikit-learn, so it is impossible to determine whether deployment will select a version affected by known advisories. In this skill context, scikit-learn is a normal ML dependency, which makes the intent benign, but the lack of version certainty still leaves a real exposure window.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

numpy is unpinned, which makes dependency resolution nondeterministic and prevents clear verification of the installed version's security posture. Given numpy's long history and multiple advisories, this creates avoidable supply-chain and patch-management risk.

Content

Scanner excerpt · requirements.txt (reported line 3)May include surrounding context.

text
jieba>=0.42.1
scikit-learn>=1.0.0
numpy>=1.21.0

Unverifiable Dependency: numpy has 16 known advisory(ies) (CVE-2014-1859 (Numpy arbitrary file write via symlink attack); CVE-2021-41495 (NumPy NULL Pointer Dereference); CVE-2021-33430 (NumPy Buffer Overflow (Disputed)) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
89% confidence
Finding

Because numpy is not pinned, the project cannot verify whether the installed release is one with known security issues. The article-analysis skill does not inherently increase exploitability, but unverified foundational libraries still raise avoidable dependency risk across environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code file contains natural-language text that fixes the skill description to Chinese ('文章品鉴师', '帮助用户提前品尝文章可读性,过滤低质量内容'). The policy requires flagging language or locale restrictions unless the skill offers user opt-in or clearly documents a justified regional scope, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The main execution block prints all headings, warnings, and dimension names in Chinese only. This reinforces a hard-coded language constraint in user-visible behavior, with no indication that users can opt into another locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code's natural-language documentation and console output are entirely in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language. Under the policy, forcing a specific language without user choice can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The main execution path prints Chinese-only output to the console, which enforces a specific language in at least one user-facing interaction. There is no nearby justification that this is a region-specific tool or any mechanism for user opt-in.

Content

No source excerpt is available for this finding.