ClawHub
Back to skill

Security audit

landscaping-bid-sheet

Security checks for vulnerabilities and agentic risk

Overview

The advertised bid generator ignores job costs and always produces zero-dollar prices, creating a material risk of underquoting.

Do not rely on this version for customer quotes until its calculations and missing bid sections are fixed and independently checked. The optional unsigned Windows app is unnecessary for the Python workflow and falls outside this review.

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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

If the reported script behavior is accurate, presenting hardcoded zero prices as calculated landscaping estimates creates an output-integrity failure that could cause underquoting, financial loss, or customer disputes. The bid-generation context makes incorrect totals consequential, although the script was not supplied and SKILL.md alone cannot independently substantiate the reported implementation defects.

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.

The skill promises a detailed landscaping bid but generates only placeholder price tiers with zero-dollar prices.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

This is a business-logic and output-integrity flaw: the script always uses a hard-coded zero base cost, ignores job-specific costing inputs, and produces zero-dollar tiers without identifying them as incomplete placeholders. In a contractor bidding workflow, these apparently usable prices could cause substantial underquoting if relied upon, although the file shows no malicious behavior or code-execution exploit.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.