财政数据采集分析

• Outcome: Pass
• Latest audit: May 28, 2026 · 6:11 AM UTC
• Version: 1.0.0

Overview

This appears to be a purpose-aligned financial data collection skill with normal scraping and local export risks, not evidence of malware or deception.

Install only if you are comfortable with the agent fetching financial data from the network and writing generated files in the workspace. Prefer running it in an isolated environment, pin and audit the Python dependencies, and review which sites it contacts and where it saves outputs before using it on sensitive projects.

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill instructs the agent to run a pipeline that performs network access and writes files into the workspace, but the skill metadata does not declare those permissions. Undeclared capabilities reduce transparency and policy enforcement, making it easier for a skill to exceed expected trust boundaries or be executed in environments that did not explicitly authorize network and filesystem effects.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests
beautifulsoup4
lxml
openpyxl

• Confidence: 98% confidence
• Finding: The dependency list is unpinned, so builds may resolve to different versions over time, including unexpectedly vulnerable or breaking releases. In a data-collection skill that scrapes external websites and processes remote content, this increases supply-chain and reproducibility risk because deployments can silently pick up insecure package versions.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests
beautifulsoup4
lxml
openpyxl

• Confidence: 98% confidence
• Finding: Leaving beautifulsoup4 unpinned makes the environment non-reproducible and allows future installs to pull different code than originally tested. For a scraping pipeline, parser behavior changes can also alter data extraction logic in unsafe or unreliable ways, compounding security and integrity risk.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests
beautifulsoup4
lxml
openpyxl

• Confidence: 98% confidence
• Finding: An unpinned lxml dependency is risky because lxml has had multiple security issues and is commonly used to parse attacker-controlled or malformed markup. In this skill, which ingests remote web content, silently resolving to an unsafe version could expose the pipeline to parser-related attacks or unsafe content handling.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests
beautifulsoup4
lxml
openpyxl

• Confidence: 98% confidence
• Finding: Unpinned openpyxl creates supply-chain and reproducibility risk, especially when handling spreadsheet exports that may come from external or semi-trusted sources. Version drift can reintroduce known XML parsing issues or change security-relevant parsing behavior without review.

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High

• Category: Supply Chain
• Confidence: 94% confidence
• Finding: The file declares requests without a version constraint, and static analysis associates that package with multiple known advisories. Because the requirement is unpinned, installation may select a vulnerable release, which is particularly dangerous for a network-facing scraping skill that makes outbound HTTP requests and may process attacker-influenced URLs or credentials.

Known Vulnerable Dependency: lxml — 10 advisory(ies): CVE-2021-43818 (lxml's HTML Cleaner allows crafted and SVG embedded scripts to pass through); CVE-2014-3146 (lxml Cross-site Scripting Via Control Characters); CVE-2021-28957 (lxml vulnerable to Cross-Site Scripting ) +7 more

High

• Category: Supply Chain
• Confidence: 95% confidence
• Finding: The file declares lxml without pinning to a patched version, and lxml has a history of security issues affecting parsing and HTML cleaning. In this skill's context, remote HTML/XML content from web scraping increases the chance that malicious or malformed input could trigger unsafe parser behavior if a vulnerable version is installed.

Known Vulnerable Dependency: openpyxl — 2 advisory(ies): CVE-2017-5992 (Improper Restriction of XML External Entity Reference in Openpyxl); CVE-2017-5992 (Openpyxl 2.4.1 resolves external entities by default, which allows remote attack)

High

• Category: Supply Chain
• Confidence: 95% confidence
• Finding: The openpyxl dependency is unpinned and associated with known XML external entity-related issues in older versions. Since this skill exports and may later process spreadsheet data, a vulnerable resolver could expose the system to XXE-style attacks or unsafe file parsing if untrusted workbook content is introduced.

Static analysis

No suspicious patterns detected.