Security News Feed

• Outcome: Review
• Latest audit: Sep 11, 2026 · 1:20 PM UTC
• Version: 1.0.1

Overview

This security-news skill mostly matches its stated purpose, but it can automatically change Notion records and publish AI-generated content with unclear safeguards.

Review before installing. Use a dedicated Notion database and a least-privilege Notion integration, disable or patch the automatic 90-day archival, keep Tistory disabled unless you intend browser-session publishing, pin dependencies, and require review before publishing AI-generated summaries from crawled content.

A.I.G

Vulnerability Patterns

• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs
• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions

Findings (4)

T05 · Unauthorized Access and Privilege Escalation

Error

• Location: security_news_aggregator.py:446

Finding

Undocumented Automatic Archival of Remote Notion Records

Content

View full analysis

Remediation

View remediation

T09 · Insecure Skill Coding Practices

Error

• Location: security_news_aggregator.py:366

Finding

Indirect Prompt Injection Through Crawled News Content

Content

View full analysis

Remediation

View remediation

T09 · Insecure Skill Coding Practices

Error

• Location: modules/crawlers/skshieldus.py:30

Finding

TLS Certificate Verification Disabled in Multiple Crawlers

Content

View full analysis

Remediation

View remediation

T08 · Insecure Dependencies

Warning

• Location: requirements.txt:2

Finding

Unpinned Runtime Dependencies Create Supply-Chain Risk

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger

Findings (199)

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 317)May include surrounding context.

md

### Tistory API (선택)
1. https://www.tistory.com/guide/api/register 접속
2. 앱 등록
3. Access Token 발급

## 라이선스

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 · SKILL.md (reported line 108)May include surrounding context.

md

from typing import Optional, List, Dict, Any
from dotenv import load_dotenv

# .env 파일 로드 (상위 디렉토리 탐색)
import sys
from pathlib import Path

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 · config.py (reported line 13)May include surrounding context.

python

from typing import Optional, List, Dict, Any
from dotenv import load_dotenv

# .env 파일 로드 (상위 디렉토리 탐색)
import sys
from pathlib import Path

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 · config.py (reported line 17)May include surrounding context.

python

from typing import Optional, List, Dict, Any
from dotenv import load_dotenv

# .env 파일 로드 (상위 디렉토리 탐색)
import sys
from pathlib import Path

Credential Access

High

• Category: Privilege Escalation
• Confidence: 76% confidence

Finding

Automatically loading the first .env found while walking up parent directories can cause the application to trust configuration and secrets from an unintended location. In a shared filesystem, mispackaged deployment, or attacker-influenced directory structure, this could inject malicious API keys, webhook URLs, or service endpoints and redirect sensitive operations.

Content

Scanner excerpt · config.py (reported line 21)May include surrounding context.

python

current_path = Path(__file__).resolve()
search_paths = [current_path]  # 현재 디렉토리
for _ in range(4):  # 최대 4단계 상위 경로 검색
    env_file = current_path / '.env'
    if env_file.exists():
        load_dotenv(env_file)
        break

Chaining Abuse

High

• Category: Tool Misuse
• Confidence: 75% confidence

Finding

Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

Content

Scanner excerpt · modules/prompts/blog_generation.py (reported line 193)May include surrounding context.

python

\`\`\`markdown
\`\`\`bash
# 패치 적용
sudo apt update && sudo apt upgrade
\`\`\`
\`\`\`

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 · all_crawlers_final.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · check_notion.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · final_8_crawlers.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · final_test.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · full_pipeline.py (reported line 17)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · integration_test.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · rss_quick_test.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · selenium_test.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · test_13_crawlers.py (reported line 15)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · test_8_crawlers.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · test_9_crawlers.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · test_all_active.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · test_all_crawlers.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · test_crawlers.py (reported line 14)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · test_mermaid.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

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 · test_notion_publish.py (reported line 13)May include surrounding context.

python

# 환경 변수 로드
from dotenv import load_dotenv
env_file = Path.home() / '.openclaw' / 'workspace' / '.env'
load_dotenv(env_file)

from modules.crawlers.krcert import KRCERTCrawler

Context-Inappropriate Capability

High

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The code publishes crawled and LLM-generated content to Notion, an external service, without any available context establishing that publication is within the skill's authorized scope. In a security review context, undeclared exfiltration or outbound publication is dangerous because it can transfer sensitive, copyrighted, or manipulated content to third-party systems.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The trigger phrases include very broad terms like 'security news' and '뉴스 수집', which can overlap with ordinary user requests and cause the skill to activate unexpectedly. Because this skill performs external collection, summarization, and possible publication, accidental invocation can lead to unintended network activity and data handling beyond the user's intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill description explains functionality but does not clearly warn users that collected content is sent to Gemini and may be stored or published to Notion and Tistory. This creates a transparency and consent problem: users may invoke the skill without realizing data will leave the local environment and potentially be posted externally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.