Back to skill

Security audit

codebase-auditor

Security checks for vulnerabilities and agentic risk

Overview

This skill locally inventories important project configuration and credential-related filenames for backup planning, without reading file contents or sending data elsewhere.

Install only if you are comfortable creating a local manifest of sensitive file locations such as .env files and private-key filenames. Keep the generated JSON private, choose a project directory deliberately, and avoid sharing the inventory with untrusted tools or people.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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 (7)

Credential Access

High
Category
Privilege Escalation
Confidence
94% confidence
Finding

The skill is explicitly designed to discover and inventory highly sensitive artifacts including .env files, private keys, service-account files, and credential bundles. Even if it claims not to read contents, enumerating and packaging the exact locations and types of secrets creates a high-value map for follow-on theft, backup exfiltration, or privilege escalation, and the surrounding context increases risk because the output is intended for downstream tooling.

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

md
1. **环境文件**:识别所有 `.env`、`.env.*`、`*.env` 文件——这些文件包含应用程序运行所需的运行时配置和凭据。
2. **配置文件**:定位 `config.json`、`*.config.js`、`*.config.ts`、`application.yml` 及类似的结构化配置文件。
3. **凭据文件**:检测 `credentials.json`、`*.pem`、`*.key`、`service-account.json` 及其他可能包含认证材料的文件。
4. **CI/CD 配置**:包含 `.github/workflows/*.yml`、`.gitlab-ci.yml`、`Dockerfile`、`docker-compose.yml`——这些文件定义了部署流水线的配置。
5. **数据库配置**:查找 `database.yml`、`knexfile.js`、`prisma/schema.prisma` 等数据库连接配置文件。

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · script/scan.py (reported line 6)May include surrounding context.

python
from datetime import datetime

CRITICAL_PATTERNS = [
    '.env', '.env.*', '*.env',
    'config.json', '*.config.js', '*.config.ts',
    'application.yml', 'application.properties',
    'credentials.json', '*.pem', '*.key', 'service-account.json',

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · script/scan.py (reported line 39)May include surrounding context.

python
from datetime import datetime

CRITICAL_PATTERNS = [
    '.env', '.env.*', '*.env',
    'config.json', '*.config.js', '*.config.ts',
    'application.yml', 'application.properties',
    'credentials.json', '*.pem', '*.key', 'service-account.json',

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · script/scan.py (reported line 9)May include surrounding context.

python
'.env', '.env.*', '*.env',
    'config.json', '*.config.js', '*.config.ts',
    'application.yml', 'application.properties',
    'credentials.json', '*.pem', '*.key', 'service-account.json',
    '.github/workflows/*.yml', '.gitlab-ci.yml', 'Jenkinsfile',
    'Dockerfile', 'docker-compose.yml',
    'database.yml', 'knexfile.js', 'prisma/schema.prisma',

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill describes repository scanning and generation of a JSON manifest, which implies filesystem access and likely file output, but it does not declare any explicit tool scope or permissions boundaries. That makes the effective access ambiguous and can allow broader-than-necessary file read/write behavior, especially dangerous because the scan targets sensitive files such as environment, key, and credential artifacts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's natural-language description and all user-facing documentation are entirely in Chinese, with no indication that other languages are supported or that the language is a deliberate region-specific constraint. Per 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.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest describes scanning a project directory and generating a JSON inventory of key configuration files, which implies analysis of existing files. The code also creates an output directory and writes the resulting inventory to disk, which is additional write behavior not explicitly stated in the description, even though it is related to the skill's purpose.

Content

No source excerpt is available for this finding.