batch-files

From the files and frontmatter at commit 8178d19. This is how much a skill can do, not whether it is risky.

• Touches credentials

  It reads, asks for or contains keys, tokens, passwords or similar secrets.

  references/batch-files-and-functions.md:79 (opens in a new tab)

• Downloads software

  It fetches programs or packages from the internet, or from a package source other than the default.

  references/windows-commands.md:671 (opens in a new tab) · references/windows-commands.md:672 (opens in a new tab) · references/batch-files-and-functions.md:282 (opens in a new tab) and 3 more

• Sets up background tasks

  It schedules jobs or startup items that can keep running after you remove the skill.

  references/batch-files-and-functions.md:274 (opens in a new tab)

• Runs shell commands

  Its instructions or files give the agent commands to run on your computer.

  references/batch-files-and-functions.md:274 (opens in a new tab) · references/windows-commands.md:671 (opens in a new tab) · references/windows-commands.md:672 (opens in a new tab) and 1 more

• Reaches the network

  It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

  references/windows-commands.md:671 (opens in a new tab) · references/windows-commands.md:672 (opens in a new tab) · references/batch-files-and-functions.md:282 (opens in a new tab) and 3 more

• Names web addresses

  It mentions outside web addresses the agent may visit. We list them but don't follow them.

  Outside links we did not follow

Pattern check: 4 items to review · commit 8178d19 · 3 Nov 2026

• R25 · CriticalScheduled task or startup item

  references/batch-files-and-functions.md:274 (opens in a new tab)

  …), `/End` (stop running task), `/ShowSid`. Create example: `SCHTASKS /Create /SC DAILY /TN "MyTask" /TR "C:\script.bat" /ST 21:00`. Schedule types: MINUTE, HOURLY, DAILY, WEEKLY, MONTHLY, ONCE, ONST…

• R01 · CriticalDownload piped into a shell

  references/windows-commands.md:671 (opens in a new tab)

  - [rundll32](https://learn.microsoft.com/en-us/windows-server/administration/windows-commands/rundll32)

• R01 · CriticalDownload piped into a shell

  references/windows-commands.md:672 (opens in a new tab)

  - [rundll32 printui](https://learn.microsoft.com/en-us/windows-server/administration/windows-commands/rundll32-printui)

• R01 · HighDownload piped into a shell

  references/batch-files-and-functions.md:282 (opens in a new tab)

  …t.Echo "message"` then `WSCRIPT msg.vbs`. MSHTA one-liner: `MSHTA vbscript:Close(MsgBox("message",vbOKOnly,"title"))`. PowerShell one-liner: `FOR /F "usebackq" %%A IN (\`PowerShell -Command "Add-Typ…

We checked every text file in this skill, at commit 8178d19 on 3 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

• Agent Skills specPasses with warnings

  The open format from agentskills.io, held to the strictest version of each rule among the agents we check.

  • Warning

    The body is 549 lines; the spec suggests under 500. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Note

    There is no license field, so readers can't tell whether they may reuse the skill. O2

    Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Note

    Reference files over 100 lines with no table of contents at the top: references/batch-files-and-functions.md (296 lines), references/cygwin.md (102 lines), references/tools-and-resources.md (126 lines) and references/windows-commands.md (833 lines). B5

    Fix: Add a short list of the sections at the top of each.

• Claude CodePasses

  Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

  • Note

    The body is 549 lines; the spec suggests under 500. Claude Code's docs say the same. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Note

    Reference files over 100 lines with no table of contents at the top: references/batch-files-and-functions.md (296 lines), references/cygwin.md (102 lines), references/tools-and-resources.md (126 lines) and references/windows-commands.md (833 lines). B5

    Fix: Add a short list of the sections at the top of each.

• Claude apps & API uploadPasses

  Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

  • Note

    The description is 464 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

    Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • Note

    The body is 549 lines; the spec suggests under 500. Anthropic's guidance says the same. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Note

    Reference files over 100 lines with no table of contents at the top: references/batch-files-and-functions.md (296 lines), references/cygwin.md (102 lines), references/tools-and-resources.md (126 lines) and references/windows-commands.md (833 lines). B5

    Fix: Add a short list of the sections at the top of each.

• OpenAI (Codex & API)Passes
• VS Code & CopilotPasses

10 files