Back to skill

Security audit

QA Reviewer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent QA helper that runs local review/test scripts and writes local reports, with no evidence of exfiltration, persistence, or hidden behavior.

Install only if Chinese-language QA guidance is acceptable. Run the scripts against the intended project directory, review project test behavior before invoking run_tests.sh, and expect local markdown report files and possible test build directories to be created.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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 (14)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

The test teardown constructs a shell command using string concatenation and executes it with system(), which is unsafe because shell execution expands metacharacters and trusts the composed command string. Although testDir_ is derived from getpid() in this example and appears low-risk in normal use, invoking rm -rf through a shell is a dangerous pattern that can become destructive if the path is influenced, malformed, or unexpectedly empty.

Content

Scanner excerpt · examples/test_case_example.cpp (reported line 29)May include surrounding context.

text
void TearDown() override {
        // 测试后清理
        std::string cmd = "rm -rf " + testDir_;
        system(cmd.c_str());
    }

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file title and introductory sections are written in Chinese, but there is no indication that the skill supports other languages or that Chinese is a required, justified locale for a region-specific use case. This can violate a language/locale policy when users are not given an explicit opt-in or alternative.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly instructs users to run bundled shell scripts for code review, report generation, and test execution, but provides no warning that these actions may execute untrusted project code, invoke project-defined test hooks, or modify files in the workspace. In an agent-skill context, that omission can lead users or automated agents to run potentially dangerous commands with undue trust, increasing the chance of unintended code execution or filesystem changes.

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 file uses only Chinese-language content, which can constitute a language/locale policy violation when no user opt-in or alternative language option is provided. The document does not indicate that it is intentionally region-specific or that users may choose another language.

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 presents all user-facing checklist content exclusively in Chinese, with no indication that language choice is optional or that the skill is region-specific. Under the policy, forcing a specific language without opt-in can be 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

This markdown file presents all workflow instructions in Chinese and does not indicate that the language choice is optional or region-specific. That can violate a language/locale policy when users are not given an opt-in or alternative language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The package description forces a specific language in user-facing metadata, which can violate language/locale policy when no user opt-in or justification is provided. Nothing in this manifest indicates the skill is intended only for a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This shell script presents all user-facing messages and the generated markdown report in Chinese, with no option to select another language or locale. That creates a natural-language locale policy issue under the rule because the skill enforces a specific language without opt-in or a documented region-specific reason.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script's comments, console output, and generated markdown report are all written in Chinese, including user-facing status messages and report content. This imposes a specific language on all users without opt-in or justification, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown template is entirely written in Chinese and presents a fixed-language review format, which can constitute a language/locale policy violation when users are not given an explicit choice. The file does not indicate that the template is region-specific or optional by locale.

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 template is entirely written in Chinese, including all section headings and field labels, which effectively imposes a specific language on report generation. The file does not provide an opt-in, alternative locale, or any justification that the template is intended only for a Chinese-language or region-specific workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file uses Chinese throughout for the publishing instructions, which can constitute a language/locale policy issue when the skill does not provide user opt-in or explain that it is intended only for a Chinese-speaking audience. The file contains no indication that the locale restriction is deliberate or optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The natural-language instructions and usage guidance are presented exclusively in Chinese, with no indication that this language choice is optional or region-specific. The policy requires avoiding forced language or locale constraints unless the user is given a choice or the constraint is clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This C++ file contains user-facing natural-language documentation entirely in Chinese, including the brief description and explanatory comments. Under the policy rule for language/locale, this is a violation when a specific language is imposed without opt-in or justification that the skill is region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.