Back to skill

Security audit

Property turnover estimate

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its report-upload workflow may send full inspection documents to a third party without a privacy warning or clear approval first.

Before installing, consider whether you are comfortable with inspection documents being sent to Tektolo. The scan is partial because some referenced paths could not be resolved, so its evidence is incomplete; review the upload and privacy steps before using the skill, and avoid sending documents with personal information unless you have reviewed and redacted them.

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 report-upload workflow lacks a privacy warning before sending entire inspection documents to a third-party service.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The workflow directs the assistant to upload entire inspection documents to Tektolo without first warning the user about third-party disclosure or requiring removal of personal information. Rental inspection reports can contain tenant names, addresses, signatures, and sensitive photos; checking extracted findings after upload cannot prevent that disclosure. Although the photo guidance prohibits sending personal details, the document-upload workflow does not explicitly apply that safeguard before transmission.

Content

No source excerpt is available for this finding.