debt-blitz-planner

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 11:13 AM UTC
• Version: 1.0.0

Overview

This is a coherent local debt-payoff calculator, with user-initiated CSV export that should be handled carefully because it may contain sensitive financial labels and has a spreadsheet formula-injection weakness.

Reasonable to install for local debt payoff planning. Avoid using attacker-provided debt names, be careful where you save CSV exports, and treat exported files as sensitive personal financial data; names beginning with characters like =, +, -, or @ should be sanitized before opening the CSV in a spreadsheet.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

• Location: scripts/debt_payoff_planner.py:267

Finding

Spreadsheet Formula Injection Through Unsanitized Debt Names in CSV Export

Content

View full analysis

Remediation

View remediation

str: if value and value[0] in ("=", "+", "-", "@", "\t", "\r"): return "'" + value return value ``` 2. Apply the function to the debt name at the CSV output boundary: ```python w.writerow([ month, csv_safe_text(name), pay / 100, max(bal, 0) / 100, ]) ``` 3. Apply equivalent protection to every future user-controlled textual CSV field, rather than relying only on validation at input time. 4. Add regression tests covering names beginning with `=`, `+`, `-`, `@`, tab, and carriage return. Verify that exported cells are stored as literal text. 5. Document that CSV exports contain user-supplied debt labels and should not be opened with formula execution enabled unless the values have been sanitized. Allowlisting debt-name characters could provide additional defense in depth, but output-boundary neutralization should remain in place because ordinary names may legitimately contain punctuation. ]]>

SkillSpector

Vulnerability Patterns

• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 77% confidence

Finding

The skill documentation instructs users to run a local Python script and export results to files, which implies shell execution and file-writing capability, but the skill declares no explicit tool scope or permissions boundary. In an agent environment, undeclared capabilities can lead to over-privileged execution, making it harder to constrain or audit what the skill is allowed to do if the referenced script or future edits perform unintended actions.

Content

No source excerpt is available for this finding.

subprocess module call

Medium

• Category: Dangerous Code Execution
• Confidence: 70% confidence

Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/test_debt_payoff_planner.py (reported line 67)May include surrounding context.

python

def test_cli():
    r = subprocess.run(
        [sys.executable, str(SCRIPT), "--debt", "Visa,4200,22.9,105",
         "--debt", "MC,1800,19.9,56", "--extra", "150"],
        capture_output=True, text=True)

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 80% confidence

Finding

This code writes a month-by-month debt payoff plan, including debt names and balances, to a user-specified CSV file. While the operation is user-initiated, there is no explicit warning in code-facing text about persisting sensitive personal financial data to disk.

Content

No source excerpt is available for this finding.