Back to skill

Security audit

1Lookup

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign verdict because they found no strong evidence of harmful behavior, though they noted a mismatch between the stated lookup purpose and an account retrieval action, plus a missing privacy notice.

The verdict is benign, but consider whether you are comfortable with the skill sending identifiers to 1Lookup and with the reported account retrieval behavior. The scan was partial because several referenced local paths were not found in the bundled artifact, so the available evidence is incomplete.

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
90% confidence
Finding

The supplied code calls /api/v1/account without any phone number, email address, or IP address input. Its sole demonstrated behavior is account retrieval, not the declared validation or enrichment functionality. Although an account check could support a larger lookup workflow, no such workflow or supporting role appears in this chunk.

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 11)May include surrounding context.

md
env:
        - ONELOOKUP_API_KEY
      bins:
        - curl
    primaryEnv: ONELOOKUP_API_KEY
    envVars:
      - name: ONELOOKUP_API_KEY

The lookup workflow lacks a user-facing privacy notice about sending identifiers to a third-party service.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow directs the agent to send phone numbers, email addresses, and IP addresses to 1Lookup without instructing it to notify the user that these identifiers will leave the conversation for third-party processing. The credit warnings and restrictions on handling returned personal data do not disclose this input-data sharing.

Content

No source excerpt is available for this finding.