Back to skill

Security audit

房地产房源信息收集与可视化分析 | Real Estate Filing Query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a real-estate public filing data workflow with proportionate browser/API collection guidance, local report output, and no executable install payload.

Install only for compliant analysis of publicly disclosed real-estate filing/listing data. Before running it, confirm the target site permits automation, avoid authenticated/private data sources, and delete or redact raw API debug caches after troubleshooting.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill's natural-language description and operational instructions are entirely presented in Chinese, indicating an implicit locale/language constraint, but there is no statement offering users a language choice or documenting a justified region-specific restriction. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The workflow directs the agent to maintain cumulative history in history/snapshots.json and project MEMORY.md across runs, but does not warn about data minimization, retention duration, or exclusion of potentially sensitive fields. Persistent cross-run storage increases the chance of unnecessary accumulation, secondary use, or later exposure of identifiers and operational metadata.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The guide explicitly instructs saving raw captured API responses to output/api_captured.json for debugging, but provides no retention limits, redaction guidance, or warning that public-data APIs can still contain personal or contractual identifiers. Even in a public real-estate context, raw responses may include fields such as contract numbers, internal IDs, tokens, or other metadata that should not be retained indefinitely.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file describes when to use the skill in broad task-oriented terms such as collecting project data, doing comparisons, and reusing the workflow across cities and platforms, but it does not define precise trigger phrases, boundaries, or non-applicable cases. That ambiguity could cause unintended invocation for general real-estate analysis requests rather than only the narrowly intended public filing-data workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.