Back to skill

Security audit

home-inspection-summary

Security checks for vulnerabilities and agentic risk

Overview

This local reporting skill has proportionate access, but its summaries need checking for omitted findings and copied repair prices.

Review every summary against the original inspection notes and remove repair prices manually. The supplied YAML template does not match the helper's Markdown-heading parser, so findings can be omitted. Use a fresh output directory because digest.md is overwritten. The optional [publisher's Windows app](https://github.com/rapidworker1/Multiple-AI-models-Toolkit) is unnecessary for this workflow and requires separate assessment.

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 preserves repair estimates despite the manifest's explicit no-estimates restriction.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The script copies every nonempty line from matching input sections into the report without checking for repair estimates or contractor pricing. Appending a no-estimates guardrail afterward does not remove prohibited content, so ordinary or deliberately crafted notes can produce a buyer-facing summary that violates the skill's explicit restriction. This is an output-integrity failure rather than code execution, with added significance because buyers may rely on the summary when making financial decisions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.