Back to skill

Security audit

fmcsa-carrier-intelligence

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it reports that caller-provided names and street addresses may be sent to an external service without a privacy warning or authorization.

Before installing, consider whether you are comfortable with names and street addresses being sent to an external service. Check which fields are transmitted and who receives them; avoid submitting personal or unrelated information unless you have reviewed and accepted that transfer.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The workflow sends caller-provided names and addresses to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The skill directs the agent to send caller-provided names and street addresses to a third-party service without first disclosing that transfer or obtaining authorization. Those claims may contain nonpublic information or personal information about sole proprietors; returning only match booleans does not protect the submitted values from the service. The explicit business-verification purpose and public-record context reduce the risk and suggest an omitted privacy safeguard rather than malicious exfiltration.

Content

No source excerpt is available for this finding.