Back to skill

Security audit

CN Financial Deep Analysis

Security checks for vulnerabilities and agentic risk

Overview

This A-share financial analysis skill is mostly coherent, but it asks users to install mutable third-party code and unpinned Python dependencies before using its core data source.

Review this skill before installing. Its analysis/reporting instructions are coherent, but install the MCP dependency only in an isolated virtual environment, pin or verify the exact Git commit and Python package versions, and treat generated investment conclusions as draft analysis requiring professional review.

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

T08 · Insecure Dependencies

Warning
Location
SKILL.md:236
Finding

Unpinned Third-Party Repository and Python Dependencies

Content
View full analysis

Vulnerability Details

File Location: SKILL.md:201, 236-237; outputs/requirements.txt:1-3
Vulnerability Type: Supply-chain exposure through mutable and incompletely pinned dependencies
Risk Level: Medium

Complete Code Snippets

SKILL.md:201:

bash
pip install -r outputs/requirements.txt

SKILL.md:236-237:

bash
git clone https://github.com/ccq1/cn-financial-mcp.git ~/cn-financial-mcp
cd ~/cn-financial-mcp && pip install -e .

outputs/requirements.txt:1-3:

text
matplotlib>=3.7.0
python-docx>=0.8.11
Pillow>=9.0.0

Technical Analysis

The documented setup process clones the current state of a third-party Git repository and installs it without pinning an audited commit, release tag, or cryptographic digest. The installed code can therefore change after this Skill has been reviewed.

The Python dependencies use minimum-version constraints rather than exact versions and do not provide package hashes. Consequently, separate installations can resolve to materially different package versions. Python package installation may execute build-backend or setup hooks, so a compromised upstream repository, package release, maintainer account, or distribution channel could cause code execution during installation.

The reviewed project does not itself prove that any current upstream component is malicious. The vulnerability is the absence of controls ensuring that the installed components are the same components that were audited.

Attack Path

  1. An attacker compromises the referenced GitHub repository, its maintainer account, or one of the permitted Python package releases.
  2. The attacker adds malicious installation hooks or runtime code to a version allowed by the documented installation commands.
  3. A user follows the instructions and runs git clone followed by pip install -e ., or installs the open-ended requirements file.
  4. Pip executes the compromised component's build or installation logic, or the malicious ...[truncated 746 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin the MCP dependency to a reviewed immutable commit rather than cloning the repository's moving default branch:
bash
git clone https://github.com/ccq1/cn-financial-mcp.git ~/cn-financial-mcp
cd ~/cn-financial-mcp
git checkout --detach <audited-commit-sha>
  1. Publish and verify the expected commit ID or signed release. Where practical, verify a release archive with a documented SHA-256 digest before installation.

  2. Replace minimum-version constraints with tested exact versions and generate a hash-locked requirements file, for example using pip-compile --generate-hashes.

  3. Install dependencies in a dedicated, unprivileged virtual environment rather than the system Python environment.

  4. Review the MCP package's build configuration, installation hooks, transitive dependencies, and runtime network behavior before approving an updated commit.

  5. Use automated dependency scanning and a controlled update process so version changes are reviewed and tested before deployment.

  6. Avoid pip install -e . for production use where possible. Build a reproducible wheel from the audited source and verify its digest before installation.

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
95% confidence
Finding

The skill is presented as a sophisticated financial-analysis system, yet the finding indicates behavior limited to Markdown-to-Word conversion and local chart embedding, with no evidence of valuation, fraud screening, or industry logic. In a finance context, this is especially risky because it can launder unverified or hallucinated content into polished deliverables that appear authoritative, increasing the chance that users rely on inaccurate investment analysis.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill is presented as a sophisticated financial-analysis system, yet the finding indicates behavior limited to Markdown-to-Word conversion and local chart embedding, with no evidence of valuation, fraud screening, or industry logic. In a finance context, this is especially risky because it can launder unverified or hallucinated content into polished deliverables that appear authoritative, increasing the chance that users rely on inaccurate investment analysis.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 201)May include surrounding context.

md
pip install -r outputs/requirements.txt

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description and invocation examples are written entirely in Chinese and frame the skill as an A-share financial analysis tool without indicating whether responses can be provided in other languages. Under the policy, locale or language constraints should either be user-selectable or explicitly justified; here the file enforces a Chinese-language interaction pattern but does not offer a language choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file is entirely written as a Chinese-only command and requires a Chinese financial analysis report, but it does not offer the user any language or locale opt-in. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown skill specifies its title, instructions, input, and output format exclusively in Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file is written entirely in Chinese and mandates specific Chinese output content and labels, but it does not indicate that language choice is optional or that the skill is intentionally restricted to a Chinese-speaking or China-specific compliance context. 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
97% confidence
Finding

This markdown file contains user-facing natural-language guidance entirely in Chinese, and there is no indication that users can select another language or that the skill is intentionally limited to a Chinese-speaking context. 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
95% confidence
Finding

The entire skill file is written in Chinese and provides no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. 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

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file presents the skill entirely in Chinese, including the command title and all instructions, with no indication that users may choose another language or locale. This can violate a language/locale policy when the skill implicitly forces a specific language without opt-in or justification.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

The dependency is specified with a lower-bound only (matplotlib>=3.7.0), which allows future unreviewed versions to be installed and prevents reproducible builds. This increases supply-chain risk because behavior and security posture can change over time, even if no specific vulnerable matplotlib version is identified here.

Content

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

text
matplotlib>=3.7.0
python-docx>=0.8.11
Pillow>=9.0.0

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
97% confidence
Finding

python-docx is unpinned (python-docx>=0.8.11), so the installed version may vary across environments and could resolve to a release with unknown security characteristics. Because this package has historical XXE-related advisories, leaving it unpinned makes it harder to verify whether deployed environments are protected.

Content

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

text
matplotlib>=3.7.0
python-docx>=0.8.11
Pillow>=9.0.0

Unverifiable Dependency: python-docx has 2 known advisory(ies) (CVE-2016-5851 (Improper Restriction of XML External Entity Reference in python-docx); CVE-2016-5851 (python-docx before 0.8.6 allows context-dependent attackers to conduct XML Exter)), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
96% confidence
Finding

The manifest does not pin python-docx, so it is impossible to verify from this file whether an affected or patched version will be installed. Since python-docx has known XXE-related advisories in older releases, this uncertainty is security-relevant, especially if the skill handles user-supplied document content.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
98% confidence
Finding

Pillow is declared as Pillow>=9.0.0, which permits a wide range of versions and undermines reproducibility. Given Pillow's history of multiple security issues, including image parsing flaws and resource-consumption bugs, an unpinned dependency can expose deployments to avoidable supply-chain and parser-related risk.

Content

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

text
matplotlib>=3.7.0
python-docx>=0.8.11
Pillow>=9.0.0

Unverifiable Dependency: Pillow has 16 known advisory(ies) (CVE-2016-2533 (Pillow buffer overflow in ImagingPcdDecode); CVE-2023-50447 (Arbitrary Code Execution in Pillow); CVE-2021-27922 (Pillow Uncontrolled Resource Consumption) +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
97% confidence
Finding

Because Pillow is unpinned, the actual installed version cannot be verified against the package's many published advisories. This matters more in a skill that may ingest charts, reports, or user-provided images, where image-parsing libraries are directly exposed to malformed input and denial-of-service or code-execution class bugs may be relevant.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The entire document is written in Chinese and provides no indication that language choice is optional or that the skill is intentionally limited to a Chinese-language or region-specific context. 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.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This README presents all user-facing instructions entirely in Chinese and does not indicate any user language selection or locale opt-in. Under the natural-language policy rules, forcing a specific language without user choice is a policy concern unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file uses Chinese throughout and does not indicate that the user can select another language or that the content is intentionally restricted to a Chinese-language audience. 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.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file presents all user-facing content exclusively in Chinese, which can amount to a language/locale policy issue when no opt-in, alternative language, or justification is provided. The policy specifically calls for flagging cases where a skill forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file presents all instructions and analysis guidance exclusively in Chinese, which may force a specific language/locale on users without explicit opt-in. The policy calls for flagging language or locale constraints when the skill does not offer a language choice or document a justified regional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This file is a markdown document, so natural-language policy checks apply. The content forces a specific language/locale for all users and does not indicate that the skill is China-specific or provide any opt-in or alternative language support.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire skill reference content is presented only in Chinese, with no indication that users may choose another language or locale. Per the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file presents all instructions and analysis content in Chinese only, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the natural-language policy rules, forcing a specific language without opt-in can be a policy violation.

Content

No source excerpt is available for this finding.