Security audit

China Stock Quant

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward China stock-analysis skill with ordinary dependency and network-use caveats, not evidence of hidden or harmful behavior.

Install in a virtual environment, consider pinning dependency versions before use, and be aware that fetching historical or realtime market data will make outbound requests to third-party market-data sources. Treat the strategy outputs as analysis/backtesting only, not trading advice or automated order execution.

A.I.G

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:17
Finding: Unpinned Third-Party Dependencies Installed from an Unrestricted Package Index
Content: View full analysis
Remediation: View remediation
pandas== numpy== matplotlib== ``` 2. Generate and verify cryptographic hashes for all direct and transitive dependencies. Install them with: ```bash python -m pip install --require-hashes -r requirements.txt ``` 3. Use a lockfile generated from a controlled environment so transitive dependencies are reproducible. 4. Explicitly use the intended trusted package index and disable unexpected supplementary indexes where appropriate: ```bash python -m pip install \ --index-url https://pypi.org/simple \ --no-extra-index-url \ --require-hashes \ -r requirements.txt ``` 5. Regularly scan the locked dependency set for known vulnerabilities and review dependency updates before changing pinned versions. 6. Recommend installation in an isolated virtual environment or container under a non-privileged account. 7. Update both `SKILL.md` and `references/api-reference.md` so users are not instructed to bypass the reproducible dependency specification. ]]>

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module docstring, function documentation, and CLI-facing strings are written entirely in Chinese, which effectively forces a specific language for users of this skill. Under the policy, locale or language restrictions should either be optional for the user or clearly justified as region-specific.
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's docstrings, usage instructions, comments, and user-facing print messages are all in Chinese, including the CLI help text. This imposes a specific language on users without any opt-in or documented region-specific justification, which matches the language/locale policy violation criteria.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill instructs users to fetch market data via akshare and real-time/intraday interfaces, but it does not disclose that these operations send network requests to third-party data providers. This can create an unexpected privacy and policy risk in environments where outbound connectivity, logging, or data egress must be explicitly disclosed or approved.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The title presents the skill content in both English and Chinese, and later sections continue using Chinese market-condition labels. This introduces a language/locale assumption without stating that the material is bilingual by design or allowing users to choose a preferred language, which can conflict with organizational language-choice policy.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module docstring, function docstrings, and runtime print messages are written in Chinese, which imposes a specific language on users of the skill. The policy allows locale constraints only when optional or clearly justified, but this file does not offer an alternative language or document a reason for the restriction.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The inline comment says this line handles a neutral MACD case, but the statement signal = signal | 0 leaves values unchanged and does not implement any substantive neutral-state transition. This is a documentation-to-code mismatch in intent, even though it is low impact and local to signal logic.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.