ClawHub
Back to skill

Security audit

Macrocosmos

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward API guide for querying Macrocosmos social-media data, with expected use of a Macrocosmos API key and outbound requests.

Install only if you are comfortable sending search terms, usernames, date filters, and your MC_API credential to Macrocosmos. Avoid using confidential, regulated, or sensitive investigative queries unless your organization approves that data sharing.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill instructs agents to send user-supplied search terms and an API credential to a third-party service, but it does not warn that prompts, usernames, keywords, and timing metadata leave the local environment. That omission can cause unintentional disclosure of sensitive investigative queries or secrets-adjacent metadata when users assume the skill is purely local.

External Transmission

Medium
Category
Data Exfiltration
Content
---

## curl Examples

### 1. Keyword Search on X
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
"limit": 10
}

response = requests.post(url, json=payload, headers=headers)
data = response.json()

for tweet in data["data"]:
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.