Security audit

Excel Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent CSV-to-Excel report converter, with some ordinary hardening gaps users should understand before using it on untrusted files.

Install and use this only for CSV files you trust, or review/sanitize formula-prefixed fields before opening or sharing the generated workbook. Prefer running it in an isolated environment with a pinned openpyxl version instead of installing an unpinned package globally.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/csv_to_excel_report.py:94
Finding: Spreadsheet Formula Injection Through Unsanitized CSV Fields
Content: View full analysis
Remediation: View remediation
str: if value.lstrip().startswith(FORMULA_PREFIXES): return "'" + value return value ``` The exact escaping policy should be tested against all supported spreadsheet applications because formula interpretation can vary. ]]>

T08 · Insecure Dependencies

Note

Location: SKILL.md:39
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation
\ --hash=sha256: ``` Install it with: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` ]]>

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (1)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill instructs the agent to locate and read arbitrary CSV files but does not declare any explicit tool scope, permissions, or allowed-tools restrictions. That creates an authorization gap where the agent may access files beyond the intended user-provided CSV, increasing the risk of unintended local file disclosure if the skill is invoked broadly or manipulated through path inputs.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.