Back to skill

Security audit

home-inspection-summary

Security checks for vulnerabilities and agentic risk

Overview

The skill performs a limited local task, but its reports need careful checking for omitted findings and copied prices.

Compare every report against the original inspection before sharing it. The supplied YAML format currently loses findings, and the script does not remove prices from supported Markdown notes. Choose a dedicated output folder because digest.md is overwritten. The optional Windows application is unnecessary for this workflow and is outside this verdict.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The summary copies repair estimates from input despite the manifest's explicit exclusion of repair costs.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The script copies every nonempty line from matching input sections into the digest without excluding repair estimates or contractor pricing. Appending a rule against estimates does not prevent their inclusion, so ordinary or deliberately crafted notes can violate the skill's explicit no-cost requirement and expose buyers to unsupported financial guidance. This is an output-integrity and scope-enforcement issue, not evidence of code execution or data exfiltration.

Content

No source excerpt is available for this finding.