ClawHub
Back to skill

Security audit

Bilibili Analytics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Bilibili search scraper and report generator, with some install and output-sanitization cautions but no evidence of hidden, destructive, or unrelated behavior.

Install only if you are comfortable with browser automation contacting Bilibili and writing local JSON/Markdown reports. Prefer a pinned, project-local agent-browser install, do not run install commands with sudo/root, review generated Markdown as untrusted public web content, and keep page counts/rate limits conservative.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
INSTALL.md:69
Finding

Unpinned Global Installation of a Third-Party Browser Automation Package

Content
View full analysis
Remediation
View remediation
``` 2. Install the package as a project-local dependency instead of globally, and invoke it through `npx --no-install` or a package script. 3. Commit a lockfile containing resolved package versions and integrity values. 4. Verify the official package name, publisher, registry URL, release provenance, and checksums before recommending installation. 5. Review npm lifecycle scripts and consider installation with lifecycle scripts disabled when compatible: ```bash npm ci --ignore-scripts ``` 6. If a separate browser-component installation step is unavoidable, document exactly which hosts, artifacts, hashes, and filesystem locations it uses. 7. Avoid recommending `--with-deps` as a generic troubleshooting step. List required system packages explicitly and require users to review them before privileged installation. 8. Advise users not to run npm or browser installation commands as root or through `sudo`. ]]>

T09 · Insecure Skill Coding Practices

Note
Location
scripts/analyze_data.py:129
Finding

Untrusted Bilibili Metadata Is Written to Markdown Without Escaping

Content
View full analysis
Remediation
View remediation
", ">") return value ``` Apply this function to every scraped field before constructing table rows. ]]>

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

声明强调“数据分析和可视化报告”以及“追踪热门趋势”，但提供的代码只完成了基础搜索结果抓取与简单计数输出。它没有进行统计分析、趋势计算、报告生成或可视化，也没有任何跨时间追踪热门趋势的逻辑。代码的核心行为与声明中的“搜索B站视频、支持多页面抓取”部分一致，但整体描述明显夸大了实际能力，因此应判定为描述与行为不完全一致。

Content

No source excerpt is available for this finding.

File System Enumeration

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.

Content

Scanner excerpt · INSTALL.md (reported line 41)May include surrounding context.

bash
# 检查文件
ls -la ~/.openclaw/workspace/skills/bilibili-analytics/

# 应该看到：
# SKILL.md

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The installation guide states that the AI will automatically read the skill, execute a scraping script, run an analysis script, and generate a report, but it does not warn users that this will trigger network access and automated data collection. In an agent context, hidden browser automation and scraping can cause unexpected outbound requests, interact with third-party services, and collect data without clear user awareness or consent.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill instructs use of local scripts such as scripts/scrape_videos.sh and scripts/analyze_data.py, which implies file read/write capability, but it declares no explicit tool scope or permissions. That creates an avoidable trust gap: an agent or reviewer cannot tell from metadata what filesystem access is required, increasing the chance of over-broad execution in environments where tool access is policy-controlled.

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 presents the skill usage entirely in Chinese, including all example user requests, with no indication that other languages are supported or that Chinese is required for a justified region-specific reason. This can violate language/locale policy because it implicitly constrains interaction to a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains natural-language strings that force a specific language/locale for the script description and usage instructions. The policy allows locale constraints only when users are given a choice or the restriction is clearly documented and justified, 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
80% confidence
Finding

The file presents all user-facing instructions in Chinese and does not offer an alternative language or indicate that the skill is intentionally limited to Chinese-speaking users. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.