vuln

From the files and frontmatter at commit 82ce211. This is how much a skill can do, not whether it is risky.

• Runs shell commands

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

• Reaches the network

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

• Pre-approves tools

  Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.

  SKILL.md:6 (opens in a new tab)

Pattern check: 1 item to review · commit 82ce211 · 3 Nov 2026

• R34 · HighBroad tools pre-approved in allowed-tools

  SKILL.md:6 (opens in a new tab)

  allowed-tools: Bash, Read, Glob, Grep, Edit, Write

We checked every text file in this skill, at commit 82ce211 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

    Fields outside the spec: argument-hint (read by Claude Code and VS Code), user-invocable (read by Claude Code and VS Code) and model (read by Claude Code). Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1

    Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

  • Note

    The description doesn't say when to use the skill. D6

    Fix: Add a sentence such as "Use when …" naming the requests or files that should trigger it.

  • 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.

• Claude CodePasses
• Claude apps & API uploadFails

  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.

  • Error

    Upload and packaging fail on fields outside the spec: argument-hint, user-invocable and model. O1

    Fix: Delete them, and keep your own data under metadata as text values.

• OpenAI (Codex & API)Passes with warnings

  Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

  • Warning

    Fields outside the spec: argument-hint, user-invocable and model. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

    Fix: Delete them, or move your own data under metadata as text values.

• VS Code & CopilotPasses

  VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

  • Note

    VS Code ignores fields it doesn't support: model. O1

    Fix: Delete them unless another agent you target reads them.

1 file