Back to skill

Security audit

fless-apartment-hunt

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it reports sending a housing brief to Fless before requiring privacy disclosure and broad activation that may trigger an apartment-hunting workflow without clear intent; scanner coverage is partial.

Before installing, consider whether you are comfortable with the reported transfer of your housing brief to Fless before disclosure or consent, and with broad housing-related questions potentially activating the workflow. The verdict is suspicious, not a claim of malicious intent; scanner coverage is partial, so the results do not establish that the skill is safe.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

The workflow sends the user's housing brief to Fless before requiring a privacy disclosure.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The workflow submits housing preferences to Fless to generate a link before requiring disclosure or consent for that transfer. The brief includes precise POIs and potentially sensitive household information, and the subsequent browser review and outreach approval occur after Fless has already received the submitted data. This transfer serves the skill's stated purpose rather than an apparent malicious destination, but the missing privacy boundary remains significant.

Content

No source excerpt is available for this finding.

Activation includes broad mentions of moving, neighborhoods, or rent prices without requiring apartment-hunting intent.

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding

Broad activation language can route general questions about moving, neighborhoods, or rent prices into a commercial apartment-hunting workflow without establishing that the user wants one. Public-data research is low risk, but the mandatory request_city call for unsupported cities records inferred interest externally without asking; later human approval gates do not cover that submission.

Content

No source excerpt is available for this finding.