ClawHub
Back to skill

Security audit

SaaS Pricing Tiers

Security checks for vulnerabilities and agentic risk

Overview

The advertised cost-based calculator ignores your costs and produces fixed prices without the promised margin checks, so its pricing output needs review.

Treat the generated prices as placeholders until the calculator actually uses your costs and verifies margins. Have the pricing owner independently check every figure before use. The optional Windows application is unnecessary for this workflow and requires a separate trust decision; the supplied checksum alone does not establish safety.

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

The code shares the broad goal of producing SaaS tier prices, but materially falls short of the declared calculator behavior. Only tier names affect the output; prices are fixed multiples of 75 rather than derived from user-provided costs, usage allowances, or margin targets. Local input reads and Markdown output writes are ordinary supporting operations, and no unrelated access or hidden capability is evident.

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 produces fixed-price tiers rather than cost-based tiers with included units, overage rates, and margin checks.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The script derives prices solely from hardcoded BASE_COST and MARKUP constants and each tier's position, ignoring any actual cost inputs and omitting included units, overage rates, and margin checks. Because the skill is advertised as a cost-based pricing calculator, users could mistake these unsupported prices for validated recommendations and adopt loss-making tiers; this is a financial-output integrity issue, not evidence of malicious execution or data theft.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.