gsd:audit-fix

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.

• Pre-approves tools

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

  SKILL.md:8 (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:8 (opens in a new tab)

  - 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 specFails

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

  • Error

    The name "gsd:audit-fix" doesn't match its folder "audit-fix". The spec requires them to match. N4

    Fix: Set name: audit-fix, or rename the folder to gsd-audit-fix.

  • Error

    The name "gsd:audit-fix" contains ":", which reads as a namespace prefix (gsd). Only a–z, 0–9 and hyphens are allowed. N7

    Fix: Drop the prefix: name: audit-fix. Plugins add their own prefix.

  • Warning

    Fields outside the spec: type and argument-hint (read by Claude Code and VS 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.

  • Warning

    allowed-tools is a list; the spec defines a space-separated string. gh skill publish rejects a list, though Claude Code accepts one. O5

    Fix: Write it on one line: allowed-tools: Read Write Edit Bash Grep Glob Agent AskUserQuestion

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

  • Note

    The name "gsd:audit-fix" doesn't match its folder "audit-fix". Claude Code shows the skill as /gsd:audit-fix, and the folder name also invokes it. N4

    Fix: Set name: audit-fix, or rename the folder to gsd-audit-fix.

  • Note

    Claude Code ignores fields it doesn't know: type. O1

    Fix: Check the spelling against Claude Code's field list, or delete them.

• 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

    The name "gsd:audit-fix" doesn't match its folder "audit-fix". claude.ai refuses an upload whose folder name doesn't match the skill name. N4

    Fix: Set name: audit-fix, or rename the folder to gsd-audit-fix.

  • Error

    The name "gsd:audit-fix" contains ":", which reads as a namespace prefix (gsd). Only a–z, 0–9 and hyphens are allowed. N7

    Fix: Drop the prefix: name: audit-fix. Plugins add their own prefix.

  • Error

    Upload and packaging fail on fields outside the spec: type and argument-hint. O1

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

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Read Write Edit Bash Grep Glob Agent AskUserQuestion

• OpenAI (Codex & API)Fails

  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.

  • Error

    The name "gsd:audit-fix" contains ":", which reads as a namespace prefix (gsd). Only a–z, 0–9 and hyphens are allowed. N7

    Fix: Drop the prefix: name: audit-fix. Plugins add their own prefix.

  • Warning

    The name "gsd:audit-fix" doesn't match its folder "audit-fix". OpenAI's own upload example uses a differently named folder, but the spec it follows says they must match. N4

    Fix: Set name: audit-fix, or rename the folder to gsd-audit-fix.

  • Warning

    Fields outside the spec: type and argument-hint. 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.

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Read Write Edit Bash Grep Glob Agent AskUserQuestion

• VS Code & CopilotPasses with warnings

  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.

  • Warning

    The name "gsd:audit-fix" doesn't match its folder "audit-fix". VS Code uses the folder name, audit-fix, instead. N4

    Fix: Set name: audit-fix, or rename the folder to gsd-audit-fix.

  • Warning

    The name "gsd:audit-fix" contains ":", which reads as a namespace prefix (gsd). VS Code's docs say such a name fails to load; VS Code falls back to the folder name. N7

    Fix: Drop the prefix: name: audit-fix. Plugins add their own prefix.

  • Note

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

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

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Read Write Edit Bash Grep Glob Agent AskUserQuestion

1 file