Security audit

Finanças Template

Security checks for vulnerabilities and agentic risk

Overview

This is a personal finance bookkeeping skill that handles sensitive financial files, but its file reads and ledger updates are purpose-aligned and disclosed with confirmation before writes.

Install only if you are comfortable letting the agent read finance files in your workspace and analyze uploaded bank or card statements. Because the triggers are broad, review activation carefully and confirm writes only after checking the transaction summary.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill auto-activates on very broad finance-related words like 'paguei', 'comprei', 'conta', and month references, which can appear in ordinary conversation unrelated to bookkeeping. In this context, accidental activation is risky because the skill is instructed to read financial files and potentially update persistent records, increasing the chance of unintended access to sensitive data or unwanted modifications.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: Triggers like 'fatura', 'extrato', 'cartão', and 'banco' are ambiguous and can arise in general discussion without the user intending statement processing. Because this skill may parse uploaded files and classify transactions, ambiguous activation could cause unexpected handling of sensitive banking/card documents.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description says the agent reads financial workspace files and processes bank/card statements, but it does not prominently warn the user that sensitive financial data may be accessed and analyzed. In a finance skill, this omission is especially significant because bank statements, card bills, and transaction histories contain highly sensitive personal and financial information.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill states that it updates monthly and annual finance files, but it does not clearly warn users that it will make persistent changes to workspace records. This creates a risk of silent or misunderstood modification of personal financial ledgers, especially when combined with broad auto-activation and natural-language interpretation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.