ClawHub
Back to skill

Security audit

roofing-estimate-builder

Security checks for vulnerabilities and agentic risk

Overview

The skill needs review because its bundled workflow does not produce the roofing estimates and state-required legal notices it promises.

Wait for the input and template problems to be fixed before relying on this workflow. Independently check pricing and jurisdiction-specific legal notices before customer use. The optional Windows executable was not inspected and is unnecessary for the Python workflow.

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
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

If the supplied static analysis accurately describes the script, it cannot deliver the complete estimate and jurisdiction-specific terms advertised, creating an output-integrity and compliance risk rather than evidence of malicious execution. Contractors could rely on incomplete documents or unchecked totals, potentially causing financial loss or defective notices; instructions to review the output reduce but do not eliminate that risk. The script was not included, so its reported behavior cannot be independently verified here.

Content

No source excerpt is available for this finding.

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.

Static analysis

No suspicious patterns detected.