ClawHub
Back to skill

Security audit

doubao-ai-toolkit

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned and mainly adds cautious rules for using pinned Doubao/Volcano Engine AI CLI tools without exposing credentials or uploading files unexpectedly.

Install only if you intend to use Doubao/Volcano Engine services. Treat prompts and selected files as data that may leave your machine, keep ARK_API_KEY in your environment or secret manager rather than chat or command arguments, and review the pinned npm dependencies during upgrades.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

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 · SKILL.md (reported line 19)May include surrounding context.

md
const skill = fs.readFileSync(path.join(root, 'SKILL.md'), 'utf8');
const pkg = JSON.parse(fs.readFileSync(path.join(root, 'package.json'), 'utf8'));
const lock = JSON.parse(fs.readFileSync(path.join(root, 'package-lock.json'), 'utf8'));
const npmrc = fs.readFileSync(path.join(root, '.npmrc'), 'utf8');

assert.equal(pkg.dependencies['coze-coding-dev-sdk'], '0.7.32');
assert.equal(pkg.dependencies['seedream-ark'], '0.1.7');

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 · tests/security.test.cjs (reported line 9)May include surrounding context.

js
const skill = fs.readFileSync(path.join(root, 'SKILL.md'), 'utf8');
const pkg = JSON.parse(fs.readFileSync(path.join(root, 'package.json'), 'utf8'));
const lock = JSON.parse(fs.readFileSync(path.join(root, 'package-lock.json'), 'utf8'));
const npmrc = fs.readFileSync(path.join(root, '.npmrc'), 'utf8');

assert.equal(pkg.dependencies['coze-coding-dev-sdk'], '0.7.32');
assert.equal(pkg.dependencies['seedream-ark'], '0.1.7');

Static analysis

No suspicious patterns detected.