Back to skill

Security audit

Kiro Agentic IDE Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Kiro workflow guide, but it includes powerful persistent hook and MCP examples with weak safety boundaries around shell execution, credentials, filesystem access, and automatic side effects.

Review this skill before installing. Use it only if you are comfortable with Kiro project automation, and do not copy the MCP or hook examples directly into a real project without pinning packages, narrowing token scopes and filesystem paths, quoting or avoiding shell-expanded file placeholders, and checking every persistent hook that can delete, deploy, send network requests, or run on a schedule.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T08 · Insecure Dependencies

Warning
Location
references/mcp-servers.md:17
Finding

Unpinned MCP packages execute with access to sensitive credentials

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
references/hooks-reference.md:16
Finding

Unquoted file placeholders in shell-based hooks permit command injection

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/create-spec.py:125
Finding

Unsanitized spec names allow output-directory escape and file overwrite

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code only implements one small subset of the declared description: creating/managing specs, specifically scaffolding a new spec folder and template documents. It does not implement functionality for configuring hooks, setting steering rules, connecting to MCP servers, using powers extensions, or providing a complete prototype-to-production workflow. Because the declared purpose presents the skill as a broad Kiro workflow guide with multiple capabilities, while the actual code is only a spec creation script, the description materially overstates the implemented behavior.

Content

No source excerpt is available for this finding.

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 · references/mcp-servers.md (reported line 204)May include surrounding context.

md
## 环境变量管理

### 使用 .env 文件

在项目根目录创建 `.env`:

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill includes actionable instructions to create and modify files such as .kiro/hooks.yaml, .kiro/mcp.json, and steering/spec files, which implies file-write capability, but it does not declare any tool scope or permissions boundary. This creates a trust and review gap: an agent or user may assume the skill is documentation-only while it can drive persistent workspace changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description and the main instructional content are written entirely in Chinese, presenting the skill as a Chinese-only workflow guide. There is no indication that users may choose another language or that the locale restriction is required for a region-specific purpose, which matches the policy's language/locale violation criteria.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill provides MCP server configuration that includes external tool execution via npx, token-based authentication, and filesystem access to an allowed path, but it gives only minimal safety commentary. Without explicit warnings about data exposure, command trust, token handling, and the consequences of broad filesystem access, users may connect powerful external integrations unsafely.

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 contains natural-language instructions exclusively in Chinese across the full template. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown reference includes examples that automatically delete files (rm {{test_file}}), deploy to production on push, and send network requests via curl, but it does not explicitly warn readers that hooks can perform destructive or external side effects automatically. Because this is documentation, the examples may be copied directly into real configurations, so a clear warning about deletion, deployment, and outbound requests is warranted.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

该文件整体以中文编写并面向所有读者提供操作说明,但没有说明这是面向特定中文用户群的区域化文档,也没有提供语言选择或英文替代。根据语言/区域政策,这构成了未经过用户选择即强制特定语言的自然语言策略问题。

Content

No source excerpt is available for this finding.