Back to skill

Security audit

OpenClaw每日资讯汇总

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language OpenClaw news-reporting helper; its main risk is that web-sourced text is rendered into Markdown without escaping, so reports should be treated as untrusted summaries.

Install only if you are comfortable with a Chinese-language OpenClaw news-summary workflow. Treat generated reports as untrusted public-web summaries, verify important claims and links independently, and avoid feeding generated Markdown into another agent as trusted instructions without sanitization.

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/search_openclaw_news.py:305
Finding

Unsanitized search-result fields allow Markdown and HTML content injection

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/generate_report_content.py:228
Finding

Report structure accepts and renders untrusted news items without output encoding

Content
View full analysis
150: content = content[:150] + "..." markdown += f" - **摘要**:{content}\n" if item.get('url'): markdown += f" - **链接**:{item['url']}\n" ``` ### Technical Analysis `add_item_to_structure()` accepts caller-supplied news dictionaries, and `generate_markdown_content()` subsequently inserts their text fields directly into Markdown. No trust boundary is enforced between retrieved news content and the generated conversation output. The 150-character summary limit only restricts size. It does not neutralize Markdown, raw HTML, embedded images, deceptive links, multiline formatting, or control characters. The title, source, and URL fields are not length-limited in this function. Because the function is documented as producing content for direct conversation output, injected formatting reaches the user-facing rendering layer. ### Attack Path 1. An attacker controls or influences a news item supplied to `add_item_to_structure()`. 2. The item contains crafted Markdown or HTML in `title`, `source`, `content`, or `url`. 3. The item is stored unchanged in a report risk group. 4. `generate_markdown_content()` retrieves the item. 5. Lines 228-244 concatenate the malicious fields into the Markdown report without encoding or URL validation. 6. The calling agent returns the gene ...[truncated 867 chars]
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents the skill label, description, workflow, and usage guidance entirely in Chinese, which effectively forces a specific language/locale for users. The policy allows locale constraints only when users are given a choice or the restriction is clearly justified, neither of which appears here.

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 uses Chinese-only user-facing metadata such as the label and description, indicating a fixed language choice for the skill. Under the policy rule, forcing a specific language without offering user opt-in or documenting a justified locale restriction 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
93% confidence
Finding

This file is a natural-language usage guide and all instructions, examples, and headings are presented only in Chinese. Under the policy, forcing a specific language without user opt-in or a documented justification is a locale/language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring and all generated report section titles indicate the skill is designed to produce reports in Chinese by default, with no user opt-in or configurable language selection. This is a natural-language locale policy concern because the skill effectively forces a specific language across its output behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring and later report-generation strings indicate the script is specifically designed to produce Chinese-language queries and reports. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless a justified locale constraint is documented, which is not present here.

Content

No source excerpt is available for this finding.