Back to skill

Security audit

Jinjiancheng Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only investment guidance skill, but it gives actionable trading and allocation advice without enough financial-risk disclosure or suitability controls.

Review carefully before installing. Treat this as an educational market-analysis persona, not a financial advisor; verify current market data, your risk tolerance, time horizon, tax and jurisdiction constraints, and avoid acting on buy/sell or crypto-short suggestions without independent advice. If installing, prefer an immutable reviewed commit or pinned release instead of the README's unpinned command.

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
README.md:118
Finding

Unpinned Third-Party Installation Command

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 118-120
Vulnerability Type: Unpinned third-party dependency installation
Risk Level: Medium

Vulnerable Code

bash
npx skills add ting2tao/jinjiancheng-skill

Technical Analysis

The documented installation command invokes the skills npm CLI through npx without pinning the package version. It also installs the Skill from a mutable repository reference without specifying a release, tag, commit hash, checksum, or signature.

Consequently, the code executed or installed when a user follows this instruction can differ from the content reviewed during this audit. A compromised npm package, maintainer account, repository, or mutable upstream branch could introduce malicious behavior after review.

Attack Path

  1. An attacker compromises the npm package, its publishing credentials, the referenced repository, or an associated maintainer account.
  2. The attacker publishes a malicious CLI version or modifies the repository's mutable default branch.
  3. A user follows the installation command from the README.
  4. npx retrieves and executes the unpinned CLI, which then retrieves the mutable Skill content.
  5. The malicious component executes or is installed under the privileges of the user running the command.

Impact Assessment

Successful exploitation could permit arbitrary code execution with the installing user's privileges. Depending on the user's environment, this may expose source code, accessible credentials, configuration files, and other user-readable data. It could also modify files or install additional malicious components within that user's permission boundary.

The audited project itself contains no bundled executable scripts, credential access, persistence mechanism, destructive operation, or confirmed malicious payload. The risk arises from the mutable external installation chain rather than from embedded project code.

Remediation
View remediation

Remediation Suggestions

  1. Pin the skills npm CLI to a reviewed, exact version rather than allowing npx to resolve the latest release.
  2. Pin the Skill source to an immutable commit hash or signed release instead of a mutable repository branch.
  3. Publish and document cryptographic checksums or signatures for release artifacts.
  4. Instruct users to verify the source revision and integrity metadata before installation.
  5. Use a locked dependency manifest where supported and review dependency changes before updating pinned versions.
  6. Avoid installation flows that execute newly downloaded package code automatically when a non-executing retrieval and verification step is available.
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (13)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README markets the skill as a practical framework for deciding what to buy, avoid, add, trim, and rotate, but does not clearly warn up front that outputs are not financial advice and may materially affect users' finances. In this context, the omission can cause users to over-trust generated recommendations as personalized investment guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The examples provide concrete buy/sell timing, staged entry, trimming, and allocation guidance without an upfront risk warning immediately attached to those examples. Because the skill is explicitly framed around actionable market decisions, these examples can nudge users toward real trading behavior while understating uncertainty, suitability, and loss risk.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The installation command uses npx skills add ting2tao/jinjiancheng-skill without pinning a specific version or immutable reference. This creates a supply-chain risk: users may install a newer or compromised package than the author intended, and README-driven copy/paste installation increases the chance of silent execution of unreviewed code.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file presents the skill entirely in Chinese and names a Chinese-language response persona, but nowhere offers the user a language/locale option or states that the skill is limited to Chinese-speaking users for a documented regional purpose. Under the policy rule, forcing a specific language without opt-in is a natural-language locale-policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill provides concrete buy/sell timing, position sizing, staged entry, and portfolio rotation instructions that could materially influence a user's financial decisions, yet it lacks a clear warning that the output is not financial advice and may be wrong or unsuitable. In context, the detailed and authoritative tone makes users more likely to rely on it as personalized investment guidance.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is scoped for US stock and ETF evaluation, but it also introduces directional cryptocurrency trading guidance, including short-selling. That expands the behavior into a riskier asset class and strategy family without corresponding guardrails, suitability checks, or scope disclosure, increasing the chance of harmful financial guidance outside the declared purpose.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The demo content gives concrete investment-oriented suggestions such as staged buying, adding to positions, trimming winners, and reallocating proceeds, but it provides no risk disclosure, suitability caveat, or statement that the content is educational rather than personalized financial advice. In a skill explicitly meant for evaluating stock and ETF strategies, users may rely on these examples as actionable guidance, increasing the chance of financial harm or inappropriate use without understanding risks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate that language choice is optional or limited to a justified region-specific context. Under the policy, natural-language content that imposes a specific language without user opt-in should be flagged.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file presents all operational guidance in Chinese and does not indicate that the user has opted into Chinese or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The examples and responses are presented exclusively in Chinese, which can be a language/locale policy concern when the skill does not offer a user choice or document that it is intentionally region- or language-specific. There is no visible opt-in, bilingual support, or justification for restricting the content to Chinese only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains natural-language guidance only in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file is entirely written in Chinese and provides no indication that the language choice is optional or tied to a documented region-specific requirement. Under the policy rule for natural-language violations, a forced locale without user opt-in can be a compliance issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The file's user-facing natural-language content is entirely in Chinese and does not indicate any language choice, opt-in, or region-specific justification. 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.