Security audit

Singapore Condo Analysis (ChatProperty via Finch)

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly routes Singapore property questions to Finch/ChatProperty and requires approval before paid runs.

Your question will be processed by Finch/ChatProperty, so avoid including private personal or financial details. Confirm free-run availability; paid runs require your explicit approval. Review connection permissions before adding the MCP server.

A.I.G

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

SkillSpector

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 the user's input to Finch/ChatProperty without a user-facing privacy warning.

Medium

Category: Output Handling
Confidence: 90% confidence
Finding: The skill instructs the agent to create an external task using the user's input. Although Finch and ChatProperty are named, the workflow does not instruct the agent to warn the user that their query will be shared with these third-party services.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.