Back to skill

Security audit

x402-trust-check

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this skill as benign because the reported hostname lookup appears relevant to its purpose, while noting that it can disclose the destination hostname and the scan evidence is incomplete.

The verdict is benign with medium confidence, not risk-free. Before installing, consider whether you are comfortable with the rating provider receiving the hostname of services you intend to pay; the scanner says full paths and credentials are excluded. Coverage is marked partial because several local path-like references could not be resolved, so the evidence does not establish what those references lead to.

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 (2)

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 23)May include surrounding context.

md
## 1. Get the host

Take the hostname of the URL you are about to pay (for `https://api.example.com/v1/x` the host
is `api.example.com`). If the recipient is only a wallet address (no host), it is **unlisted**:
see step 4.

The mandatory rating lookup discloses the intended service's hostname to a third party without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill requires contacting agenteconomy.report before every x402 payment, placing the intended service's hostname in the request path without a privacy warning or consent step. This allows the rating provider to observe intended service usage and potentially correlate it with request timing and client network metadata; the lookup is relevant to the skill's purpose and excludes full paths and credentials, which limits but does not eliminate the privacy risk.

Content

No source excerpt is available for this finding.