Back to skill

Security audit

Eu Company Check

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its instructions use an unpinned `agentcash@latest` command for paid requests, so the code run may change without review.

Before installing, consider whether you are comfortable sending company identifiers to Glyphcall and using a package whose version can change without review. The scanners inspected the listed skill component completely, but that does not establish the safety of future `agentcash@latest` releases.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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 25)May include surrounding context.

md
| Task | Endpoint | Price |
|------|----------|-------|
| KYB bundle | `https://api.glyphcall.com/pack/kyb-eu?...%60= | $0.02 |
| VAT validation | `https://api.glyphcall.com/vat/validate?vat=<number>` | $0.01 |
| E-invoice check | `https://api.glyphcall.com/pack/einvoice-check?...%60= | $0.01 |
| Sanctions screen | `https://api.glyphcall.com/sanctions/check?name=<name>` | $0.01 |

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.

| KYB bundle | https://api.glyphcall.com/pack/kyb-eu?...%60= | $0.02 | | VAT validation | https://api.glyphcall.com/vat/validate?vat=| $0.01 | | E-invoice check |https://api.glyphcall.com/pack/einvoice-check?...%60= | $0.01 | | Sanctions screen | https://api.glyphcall.com/sanctions/check?name=<name> | $0.01 |

sh
npx agentcash@latest check "https://api.glyphcall.com/vat/validate?vat=DE123456789"

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 26)May include surrounding context.

md
| Task | Endpoint | Price |
|------|----------|-------|
| KYB bundle | `https://api.glyphcall.com/pack/kyb-eu?...%60= | $0.02 |
| VAT validation | `https://api.glyphcall.com/vat/validate?vat=<number>` | $0.01 |
| E-invoice check | `https://api.glyphcall.com/pack/einvoice-check?...%60= | $0.01 |
| Sanctions screen | `https://api.glyphcall.com/sanctions/check?name=<name>` | $0.01 |

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 32)May include surrounding context.

sh
npx agentcash@latest check "https://api.glyphcall.com/vat/validate?vat=DE123456789"
npx agentcash@latest fetch "https://api.glyphcall.com/vat/validate?vat=DE123456789"

Always check the parameter names with agentcash check first; a failed validation is not charged.

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 27)May include surrounding context.

|------|----------|-------| | KYB bundle | https://api.glyphcall.com/pack/kyb-eu?...%60= | $0.02 | | VAT validation | https://api.glyphcall.com/vat/validate?vat=| $0.01 | | E-invoice check |https://api.glyphcall.com/pack/einvoice-check?...%60= | $0.01 | | Sanctions screen | https://api.glyphcall.com/sanctions/check?name=<name> | $0.01 |

sh

The validation workflow lacks a notice that submitted counterparty identifiers are sent to a third-party service.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

The example workflow sends the VAT number to api.glyphcall.com, but the skill does not warn users that their submitted identifiers will be disclosed to this intermediary. Stating that results come from official registers and VIES describes the sources, not the third-party handling of user-supplied data.

Content

No source excerpt is available for this finding.

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.

| Sanctions screen | https://api.glyphcall.com/sanctions/check?name=<name> | $0.01 |

sh
npx agentcash@latest check "https://api.glyphcall.com/vat/validate?vat=DE123456789"
npx agentcash@latest fetch "https://api.glyphcall.com/vat/validate?vat=DE123456789"

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

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The command uses agentcash@latest, allowing the executed package version to change without review. A compromised release could execute code with the agent's permissions and potentially access credentials or payment capabilities; this is an unpinned CLI dependency, not evidence of an MCP server.

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 command executes the mutable agentcash@latest dependency rather than a reviewed, fixed release. A malicious or compromised update could run with the agent's permissions, with additional concern because this workflow involves paid requests.

Content

No source excerpt is available for this finding.