ClawHub
Back to skill

Security audit

Marsbit News

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Marsbit crypto-news lookup skill, with the main caution that user search terms may be sent to Marsbit's external API.

Install this if you are comfortable using Marsbit as an external crypto-news source. Avoid putting secrets, private wallet details, or sensitive personal information in search terms, since searches and article lookups go to Marsbit's API.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The README explicitly defines a third-party API base URL, confirming that the skill depends on external network access and data exchange with a remote service. By itself this is expected functionality, but in the context of an agent skill it creates a real data-exposure surface if prompts, keywords, or other user-derived content are sent off-platform without disclosure or controls.

Content

Scanner excerpt · README.md (reported line 31)May include surrounding context.

md
## API Base

https://api.marsbit.co/info/ai

## Available APIs

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The skill is designed to transmit user-derived queries and article IDs to an external domain, api.marsbit.co. Any external transmission can expose user interests, search terms, metadata, and usage patterns to a third party, especially when broad triggers cause activation without explicit source selection.

Content

Scanner excerpt · skill.md (reported line 20)May include surrounding context.

md
Base API

https://api.marsbit.co/info/ai


---

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · skill.md (reported line 43)May include surrounding context.

md
Example

https://api.marsbit.co/info/ai/articles/latest?limit=5

Response Example

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · skill.md (reported line 82)May include surrounding context.

md
Example

https://api.marsbit.co/info/ai/articles/latest?limit=5

Response Example

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · skill.md (reported line 121)May include surrounding context.

md
Example

https://api.marsbit.co/info/ai/articles/latest?limit=5

Response Example

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · skill.md (reported line 144)May include surrounding context.

md
Example

https://api.marsbit.co/info/ai/articles/latest?limit=5

Response Example

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · skill.md (reported line 181)May include surrounding context.

md
Example

https://api.marsbit.co/info/ai/articles/latest?limit=5

Response Example

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrases are very broad generic news intents such as 'latest crypto news' and 'Bitcoin news', which can cause this skill to activate for common user requests without clear user intent to use Marsbit specifically. This creates an overbroad routing risk where user queries may be unnecessarily sent to an external third-party news API, affecting privacy and tool-selection integrity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README advertises multiple external API operations for agents but does not clearly warn that using the skill will trigger outbound network requests and transmit user prompts or query terms to a third-party service. In an agent ecosystem, this is a real transparency and privacy issue because users may unknowingly cause external data disclosure when asking the agent to fetch or search news.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The response examples and article titles are presented in Chinese, but the skill does not say it will preserve the user's preferred language or ask for language choice. This can create a locale-policy issue if the agent surfaces Chinese-only content or titles by default to users who did not opt in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.