Back to skill

Security audit

Wallet Risk Triage

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it runs an unpinned, changeable agentcash package and sends wallet addresses to a third-party service without a privacy notice; the scanners did not establish malicious intent.

Before installing, verify that you trust the service receiving wallet addresses and are comfortable sharing them, including any request or payment metadata. Treat the mutable `agentcash@latest` command as a significant caution; consider waiting until the package version is pinned and reviewed.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

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 28)May include surrounding context.

md
| Task | Endpoint | Price |
|---|---|---|
| Sanctions screen | `https://api.glyphcall.com/sanctions/check?address=<addr>` | $0.009 |
| Token rug verdict | `https://api.glyphcall.com/token/verdict?token=%2A%2A%2A<addr>` | $0.01 |
| Wallet portfolio | `https://api.glyphcall.com/wallet/portfolio?address=<addr>` | $0.005 |
| Merchant/counterparty trust | `https://api.glyphcall.com/merchant/trust?name=<domain>` | $0.02 |

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 30)May include surrounding context.

md
|---|---|---|
| Sanctions screen | `https://api.glyphcall.com/sanctions/check?address=<addr>` | $0.009 |
| Token rug verdict | `https://api.glyphcall.com/token/verdict?token=%2A%2A%2A<addr>` | $0.01 |
| Wallet portfolio | `https://api.glyphcall.com/wallet/portfolio?address=<addr>` | $0.005 |
| Merchant/counterparty trust | `https://api.glyphcall.com/merchant/trust?name=<domain>` | $0.02 |

Use the agentcash client so payment and retries are handled:

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 31)May include surrounding context.

md
| Sanctions screen | `https://api.glyphcall.com/sanctions/check?address=<addr>` | $0.009 |
| Token rug verdict | `https://api.glyphcall.com/token/verdict?token=%2A%2A%2A<addr>` | $0.01 |
| Wallet portfolio | `https://api.glyphcall.com/wallet/portfolio?address=<addr>` | $0.005 |
| Merchant/counterparty trust | `https://api.glyphcall.com/merchant/trust?name=<domain>` | $0.02 |

Use the agentcash client so payment and retries are handled:

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 36)May include surrounding context.

Use the agentcash client so payment and retries are handled:

sh
npx agentcash@latest check "https://api.glyphcall.com/sanctions/check?address=0x..."
npx agentcash@latest fetch "https://api.glyphcall.com/sanctions/check?address=0x..."

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 37)May include surrounding context.

sh
npx agentcash@latest check "https://api.glyphcall.com/sanctions/check?address=0x..."
npx agentcash@latest fetch "https://api.glyphcall.com/sanctions/check?address=0x..."

A blocked or unverifiable check is not the same as a clean verdict. Report the signals you actually

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 29)May include surrounding context.

md
| Task | Endpoint | Price |
|---|---|---|
| Sanctions screen | `https://api.glyphcall.com/sanctions/check?address=<addr>` | $0.009 |
| Token rug verdict | `https://api.glyphcall.com/token/verdict?token=%2A%2A%2A<addr>` | $0.01 |
| Wallet portfolio | `https://api.glyphcall.com/wallet/portfolio?address=<addr>` | $0.005 |
| Merchant/counterparty trust | `https://api.glyphcall.com/merchant/trust?name=<domain>` | $0.02 |

The workflow sends wallet addresses to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow lacks an explicit privacy notice or authorization boundary for disclosing queried addresses to the provider. Although blockchain addresses are generally public and the destination is documented, request metadata and payment activity could associate an address with a requester or reveal confidential counterparty interest.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx agentcash'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The command executes agentcash@latest, allowing the downloaded executable to change without review or a skill update. A compromised future release could execute with the agent's local permissions, which is particularly concerning in a payment-capable environment; the issue is unpinned package execution, not an established MCP-server dependency.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx agentcash'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The fetch example also executes the mutable agentcash@latest package rather than a reviewed fixed release. A compromised release could run arbitrary code with the invoking agent's permissions, potentially affecting accessible credentials or payment capabilities.

Content

No source excerpt is available for this finding.