Security audit

news-homepage-fetcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language news digest workflow that fetches public news pages, translates or summarizes them, and prepares Word-ready output, with some integrity cautions around HTTP sources.

Install this only if you want a Chinese-language daily news digest workflow. Prefer HTTPS sources, review fetched article content before relying on or publishing the digest, and make sure your use of full article text complies with the selected publishers' terms.

A.I.G

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: references/source_manifest.yaml:284
Finding: Plaintext HTTP News Sources Permit On-Path Content Manipulation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (20)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The instruction says the task should be understood as extracting articles and translating them into Chinese, making Chinese output a default requirement. This is a language-policy constraint expressed in natural language, and the file does not indicate that users may opt into another language or keep source-language output.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default workflow states that English originals should be turned into Chinese titles, summaries, and full translations, while Chinese originals are standardized into Chinese summaries. Because this is presented as the standard flow rather than an optional user-selected mode, it violates the language/locale policy criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill hard-codes Chinese translation/output behavior as a default requirement rather than making language selection explicit or user-controlled. This can override user intent, create privacy/compliance issues if content is unnecessarily transformed, and reduce transparency about how outputs are produced.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The document repeatedly states that content will be translated into Chinese and output as Chinese documents, which is a language-policy constraint expressed in natural language. Because no opt-in, alternative language option, or explicit region-specific justification is provided, this fits the policy category for forced language/locale behavior.
Content: No source excerpt is available for this finding.

Skill Enumeration

Medium

Category: Agent Snooping
Confidence: 80% confidence
Finding: Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
Content: Scanner excerpt · openclaw_subagent_integration.md (reported line 17)May include surrounding context.
md
|---|---|---| | `soul.md` | subagent 核心人格与目标 | 作为该 subagent 的系统级身份说明 | | `agents.md` | 多代理分工与编排规则 | 作为 orchestrator 的代理编排文档 | | `skills/openclaw-news-homepage-fetcher/SKILL.md` | 抓取技能主说明 | 作为新闻抓取执行技能 | | `skills/openclaw-news-homepage-fetcher/references/source_catalog.md` | 新闻源清单 | 供执行前选站点时读取 | | `skills/openclaw-news-homepage-fetcher/references/source_manifest.yaml` | 机器可读源表 | 供程序化任务配置加载 | | `skills/openclaw-news-homepage-fetcher/references/translation_docx_spec.md` | 中文翻译与 Word 规范 | 供翻译与文档生成阶段读取 |

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file is entirely written in Chinese and references Chinese translation style requirements, indicating the skill is designed to operate in a fixed language. The policy allows locale constraints only when the skill offers user choice or clearly documents a justified region-specific limitation, which is not stated here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This manifest hard-codes source selection to specific language values such as English and Chinese across many entries, which constrains output/input sourcing by locale without indicating user choice or opt-in. The file does not document that the language restrictions are optional, user-configurable, or justified as a region-specific compliance requirement.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The specification requires foreign-language news to be processed into Chinese and states that English sources must produce Chinese titles, summaries, and full translations. This imposes a specific language output policy without mentioning any user selection, opt-in, or region-specific justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The description states the skill should translate articles into Chinese as part of its default behavior. This imposes a specific language choice rather than offering language selection or documenting a justified locale restriction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: This instruction defines the task as extracting news and translating it into Chinese, framing that as the intended interpretation of the skill. It does not indicate that Chinese output is optional or contingent on user preference.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The workflow explicitly directs the skill to generate Chinese titles, summaries, and full translations for English articles. This is a language-policy concern because it hard-codes a locale outcome instead of allowing user selection.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: These requirements mandate Chinese translation and Chinese summaries as minimum output fields. The file does not present this as an opt-in choice or clearly justified regional limitation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The title and purpose specify the skill reference entirely in Chinese and frame it as the default operating reference for the news-fetching workflow, while the document does not indicate that language selection is optional. Under the stated policy, forcing a specific language or locale without user opt-in 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: 87% confidence
Finding: This manifest explicitly constrains sources by fixed language values such as en and zh, beginning at L025 and repeated throughout the file, but provides no natural-language indication that users can choose or opt into a preferred language/locale. Because SQP-3 applies to all file types, this can be treated as a locale-policy concern when the skill appears to force language coverage implicitly rather than documenting user choice or a justified region-specific constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The spec repeatedly requires Chinese translation, Chinese summaries, and Chinese full text as a mandatory output format. This is a natural-language locale policy constraint, and the file does not offer users a language choice or describe this as an opt-in regional mode.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The template is entirely structured around Chinese-language output, including the title '每日新闻中文汇编', repeated '中文摘要' and '中文全文' sections, and a '翻译策略' field. This indicates a fixed Chinese locale/output requirement with no visible user opt-in or alternative language option, which matches the language/locale policy violation category.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The identity statement explicitly defines the agent as producing translated Chinese output for Chinese readers. This is a natural-language locale policy constraint, and the file does not indicate that users may choose another language or opt in to the Chinese-only behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file sets the primary success criterion as producing a Chinese daily news Word document. Because this locale requirement is mandatory and no alternative language path or opt-in is provided, it conflicts with the policy against forcing a specific language without user choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This markdown template is explicitly structured to produce Chinese output throughout, including the title and repeated fields such as '中文摘要' and '中文全文', with a '翻译策略' field reinforcing that the output is translated into Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: This markdown file defines a workflow that extracts full article content from multiple news sites, translates it, and generates output documents, but it does not include any warning about external content retrieval, copyright/site terms, or the fact that fetched content will be processed and compiled. For markdown files, SQP-2 applies when behavior affecting data, privacy, or system integrity is described without corresponding user-facing warnings.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.