ClawHub
Back to skill

Security audit

Google News Api

Security checks for vulnerabilities and agentic risk

Overview

This Google News skill does what it claims, but it asks users to paste an API key into chat and can send ordinary news queries to a third-party service with broad activation rules.

Review before installing. Use this only if you are comfortable sending search keywords and task parameters to BrowserAct. Do not paste the BrowserAct API key into chat; configure it locally as BROWSERACT_API_KEY or through an approved secret store. Be aware the script may hang if the remote task never completes.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:31
Finding

API Credential Requested Through Chat

Content
View full analysis
"Since you haven't configured the BrowserAct API Key, please go to the [BrowserAct Console](https://www.browseract.com/reception/integrations) to get your Key and provide it to me in this chat." ``` `scripts/google_news_api.py:69-74`: ```python if not api_key: print("\n[!] ERROR: BrowserAct API Key is missing.") print("Please follow these steps:") print("1. Go to: https://www.browseract.com/reception/integrations") print("2. Copy your API Key.") print("3. Provide it to me or set it as an environment variable (BROWSERACT_API_KEY).") ``` ### Technical Analysis The Skill explicitly instructs users to provide a BrowserAct API key through the chat interface. API keys are authentication secrets and should not be entered into conversational channels because chat transcripts may be retained in conversation history, telemetry, debugging records, backups, or shared logs. The script already supports retrieving the credential from the `BROWSERACT_API_KEY` environment variable. Consequently, requesting disclosure through chat is not necessary for the declared Google News collection functionality and exceeds minimum safe credential-handling requirements. The script legitimately sends the key to the declared BrowserAct HTTPS endpoint as a Bearer token. No evidence was found that it sends the credential to an unrelated destination. The vulnerability is the unnecessary chat-based acquisition method, not the authenticated API request itself. ### Attack Path 1. A user invokes the Skill without setting `BROWSERACT_API_KEY`. 2. The Skill instructs the user to paste the API key into the chat. 3. The user discloses the key in the conversation. 4. The key is retained in a transcript, telemetry ...[truncated 783 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/google_news_api.py:22
Finding

Unbounded Polling and Missing HTTP Timeouts

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill invokes a Python script, relies on an environment variable, and accesses an external API, but it does not declare any explicit tool scope or permission boundaries. This increases risk because an agent may execute code with broader-than-expected access to environment secrets and network resources, reducing transparency and reviewability for users and platforms.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are very broad and likely to match common user requests like general news lookup, trend tracking, or PR monitoring. Overbroad auto-triggering is dangerous because it can cause the agent to invoke external code and send user queries to a third-party service unnecessarily, expanding data exposure and increasing the chance of unintended execution.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/google_news_api.py (reported line 9)May include surrounding context.

python
# API Configuration
TEMPLATE_ID = "77638424152140851"
API_BASE_URL = "https://api.browseract.com/v2/workflow"

def run_google_news_task(api_key, keywords, date_range="past week", limit=30):
    headers = {"Authorization": f"Bearer {api_key}"}

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/google_news_api.py (reported line 24)May include surrounding context.

python
# 1. Start Task
    try:
        res = requests.post(f"{API_BASE_URL}/run-task-by-template", json=payload, headers=headers).json()
    except Exception as e:
        print(f"Error: Connection to API failed - {e}")
        return None

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This code sends the provided keywords and related parameters to a third-party service via HTTP requests. While the script prints errors and setup instructions, it does not clearly warn the user that their query data will be transmitted off-system to BrowserAct.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

Reading BROWSERACT_API_KEY is part of normal operation, but the code does not clearly disclose how that credential will be used beyond setup instructions. For safety-sensitive operations involving credentials, the file should explicitly state that the key is used to authenticate requests to an external service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.