sheet-mcp@r1
VERIFIED· install onlyPublisher claims: "Enables AI agents to inspect and safely edit .xlsx workbooks — reading ranges, searching cells, checking formulas, writing values or formulas, appending rows, and converting CSV — while preserving formulas and styles, dry-running edits by default, and refusing any save that would destroy charts, pivots, macros, or other features." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso openxmlformats.org, microsoft.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is sheet-mcp@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
(on Windows this needs developer mode or an elevated shell).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.b'<?xml version="1.0"?><!DOCTYPE l [<!ENTITY a "aaaaaaaaaa"><!ENTITY b "&a;&a;&a;&a;&a;&a;&a;&a;">]>'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.err, text = await call("read_range", {"path": "../etc/passwd", "sheet": "S", "range": "A1"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.(on Windows this needs developer mode or an elevated shell).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.