Back to skill

Security audit

solar-quote-calculator

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill performs limited local file operations, but its incomplete calculator requires manual verification before any customer use.

Treat this as a drafting aid rather than a working calculator. Independently calculate costs, correct the input-field mismatch, and validate missing or malformed values before sharing a quote. Choose an output folder where overwriting calculation.md is acceptable. The optional Windows application requires a separate security assessment; this verdict covers the bundled files.

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 documented net-cost calculation is never performed.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The script advertises a net-cost calculation but only echoes input values and the formula text, never computing or reporting net_cost. In a financial quoting workflow, this output-integrity defect could cause an installer or downstream agent to treat an incomplete report as a completed estimate and communicate misleading costs; the savings and incentive disclaimers do not correct this omission. There is no evidence of malicious intent or a code-execution vulnerability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.