Back to skill

Security audit

中国节假日检测

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese holiday checker with disclosed dependency checks, though users should install its unpinned Python dependency cautiously.

Install this only in a normal isolated Python environment, review or pin the `chinesecalendar` package version if supply-chain control matters, and treat any package upgrade as a user-approved maintenance action rather than something to retry automatically.

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:4
Finding

Unpinned Third-Party Dependency Creates a Supply-Chain Risk

Content
View full analysis
Remediation
View remediation
``` 2. Store dependencies in a requirements or lock file with cryptographic hashes and install them using hash enforcement: ```bash python -m pip install --require-hashes -r requirements.txt ``` 3. Generate and review hashes from a trusted package source before deployment. 4. Configure `pip` to use an explicitly trusted package index and prevent unintended fallback to untrusted or privately controlled indexes. 5. Run dependency installation and the Skill under a dedicated, least-privileged account or isolated virtual environment. 6. Review package source code and release provenance before changing the pinned version. 7. Use dependency and software-composition scanning in the release process, and update the pin only after testing and security review. 8. Keep the metadata dependency declaration consistent with the reviewed lock file so automated installers cannot silently select a different release. ]]>
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
Findings (8)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill includes shell-capable behavior via subprocess and pip commands, but the manifest declares no tool scope or permissions. That mismatch can cause the agent runtime or reviewer to underestimate what the skill may invoke, increasing the chance of unauthorized command execution or unsafe package-management actions in environments where shell access is available.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing instructions, descriptions, and response examples exclusively in Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the restriction is explicitly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill contains conflicting guidance: earlier sections instruct upgrading the package when unsupported-year detection occurs, while the SOP later warns against repeated upgrades for out-of-range years. This ambiguity can lead agents to perform unnecessary or repeated package update attempts, creating denial-of-service-like loops, inconsistent behavior, or unsafe environment changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file-level docstring is written entirely in Chinese and describes a China-specific holiday check, which imposes a language/locale assumption in natural-language content. The file does not offer any user language choice or explain a justified region-specific constraint as required by the policy.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · check.py (reported line 8)May include surrounding context.

python
def get_installed_version():
    """获取已安装的版本"""
    result = subprocess.run(
        [sys.executable, '-m', 'pip', 'show', 'chinesecalendar'],
        capture_output=True, text=True
    )

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Checking whether a date is a Chinese holiday does not inherently require spawning a subprocess to run python -m pip show. This adds an execution capability unrelated to the core purpose and expands the skill's operational surface beyond straightforward calendar evaluation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The documentation expands the skill from simple holiday lookup into subprocess-driven package inspection and upgrade guidance. Introducing package-management workflows increases attack surface and operational risk, because it encourages shell execution and environment mutation unrelated to the core user task.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest says this skill is for determining whether a date is a Chinese holiday or adjusted workday. However, the file includes additional operational behavior to invoke pip, inspect the installed package version, and gate execution on package freshness, which goes beyond simple date-status detection.

Content

No source excerpt is available for this finding.