Back to skill

Security audit

paidrouter

Security checks for vulnerabilities and agentic risk

Overview

The skill uses a disclosed fee-comparison service and shares relevant payment details without requesting access to move money.

PaidRouter receives the payment details you submit. Use approximate amounts for confidential activity, protect the retained key, and check source dates before relying on results. Public publisher and privacy information could not be independently verified.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied code performs only a key-related POST request; it does not retrieve fees, cite dated sources, compare providers, or calculate payment costs. Although API-key provisioning could support a broader implementation, the supplied chunk establishes no such connection. No local data or existing credentials are visibly transmitted.

Content

No source excerpt is available for this finding.

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 20)May include surrounding context.

Run once and keep the key (no email needed):

bash
curl -s -X POST https://paidrouter.com/api/keys -H 'content-type: application/json' \
  -d '{"use":"openclaw skill"}'

The workflow sends financial and payment-usage details to PaidRouter without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

When populated with actual owner data, the request sends payment amounts, payment frequency, and the current payment provider to a third party under a persistent API key. These details can reveal nonpublic business activity, but the workflow provides no explicit privacy notice or approval step before transmission. This is a limited privacy weakness rather than evidence of malicious exfiltration: the fields are relevant to the advertised comparison service, and no payment credentials or customer identities are requested.

Content

No source excerpt is available for this finding.