Back to skill

Security audit

Merchant Safety

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it documents running `agentcash@latest`, a mutable package version that could change between uses; the scanners did not report clear malicious intent.

Before installing, consider whether you trust the `agentcash` package and its external service, and whether you are comfortable running a version that may change over time. The scan covered the one reported component completely, but that does not establish that the skill is risk-free.

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
  • 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 (6)

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.

TaskEndpointPrice
Merchant trust verdicthttps://api.glyphcall.com/merchant/trust?name=<domain>$0.02
Full link verdicthttps://api.glyphcall.com/pack/url-safety?url=<url>$0.01
sh

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.

TaskEndpointPrice
Merchant trust verdicthttps://api.glyphcall.com/merchant/trust?name=<domain>$0.02
Full link verdicthttps://api.glyphcall.com/pack/url-safety?url=<url>$0.01
sh
npx agentcash@latest check "https://api.glyphcall.com/merchant/trust?name=example.com"

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.

| Full link verdict | https://api.glyphcall.com/pack/url-safety?url=<url> | $0.01 |

sh
npx agentcash@latest check "https://api.glyphcall.com/merchant/trust?name=example.com"
npx agentcash@latest fetch "https://api.glyphcall.com/merchant/trust?name=example.com"

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/merchant/trust?name=example.com"
npx agentcash@latest fetch "https://api.glyphcall.com/merchant/trust?name=example.com"

A missing signal is not a clean verdict. Report the fields you actually received, and treat the

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

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The command uses agentcash@latest, a mutable package reference rather than a pinned version. Running it can download and execute a newly published or compromised release with the agent's privileges; the payment-related context increases potential exposure if credentials or wallet capabilities are available.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The fetch command also executes agentcash@latest without fixing the package version. A compromised future release could execute arbitrary code in the agent's environment, and a payment-capable execution environment could increase the consequences; the text does not establish that this is an MCP server, but the dependency-pinning issue remains valid.

Content

No source excerpt is available for this finding.