ClawHub
Back to skill

Security audit

Swaps Intel

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Swaps.app blockchain risk API integration, with no local executable code or hidden persistence found.

Before installing, understand that wallet addresses, transaction hashes, and your API key are sent to Swaps.app, and any returned markdown should be treated as untrusted display content rather than instructions for the agent to follow.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (4)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · COMPLIANCE_PREPACK.md (reported line 14)May include surrounding context.

md
## Artifact Map (where to review)
1. Skill policy + required disclaimer rules  
   `skills/swaps-intel/SKILL.md`
2. Public launch README (what it is / what it is not)  
   `skills/swaps-intel/README.md`
3. API Terms (short form)

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 · README.md (reported line 30)May include surrounding context.

1. Action-based format (Recommended)

bash
curl -X POST https://system.swaps.app/functions/v1/agent-api/ \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{

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 · SKILL.md (reported line 35)May include surrounding context.

Check an address:

bash
curl -X POST https://system.swaps.app/functions/v1/agent-api \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The API explicitly marks markdown_summary as 'intended for direct use by the agent,' which encourages an agent to relay or potentially follow untrusted third-party content without applying validation, sanitization, or policy checks. In an agent setting, remote markdown can contain prompt-injection text, misleading instructions, unsafe links, or formatting crafted to manipulate downstream model behavior, making this more dangerous than ordinary presentation text.

Content

No source excerpt is available for this finding.