Index of every page on this site: llms.txt
All skills
bitwarden avatar

/workflow-audit

@a11c77b official
by bitwardenbitwarden/ai-plugins165 stars
27
Run it yourself

Run the Bitwarden workflow linter (bwwl) against one or more repos and report findings. Strictly read-only — does not modify any files. Categorizes findings as mechanical or judgment using the bitwarden-workflow-linter-rules skill. Supports single repo, multiple repos, or single file/directory scope. <example> User: Run the workflow linter on the server repo Action: Trigger workflow-audit for that repo </example> <example> User: Lint the workflows across server, clients, and android Action: Trigger workflow-audit in multi-repo mode </example>

Use this Skill: https://skilld.dev/gh/bitwarden/ai-plugins/workflow-audit

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈142 tokens for metadata: the name and description. ≈528 when used: this file.

Description uses 7.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈565 characters, or 7.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Rules

  • This skill is strictly read-only. Do not modify, create, or delete any files.
  • Flag uncertainty. If a finding is ambiguous, note it in the report rather than guessing.

Step 1: Verify Prerequisites

Check if bwwl is available:

bwwl --version

If the command is not found, stop and inform the user that bwwl must be installed before continuing. Do not attempt to install it.

Step 2: Determine Scope

Parse the user's request to determine what to lint:

  • Single file or directory (e.g., .github/workflows/build.yml or .github/workflows/): Operate on the current repo only.
  • Multiple repos (e.g., "server, clients, android"): Operate on each repo sequentially. Ask the user for the base directory where their repos are cloned. For each repo, look for its local clone at <base-dir>/<repo>. If a clone is not found, inform the user and skip that repo.
  • No specific target: Lint all files in .github/workflows/ of the current directory.

Step 3: Run the Linter

For each repo in scope, run:

bwwl lint -f .github/workflows/

Capture both stdout and stderr. If operating on multiple repos, announce which repo is being linted.

Step 4: Parse and Categorize Findings

From the linter output, produce a structured list of findings. Group by file and rule. Consult the bitwarden-workflow-linter-rules skill to categorize each finding:

Mechanical (can be auto-fixed):

  • name_capitalized, permissions_exist, pinned_job_runner, step_pinned, underscore_outputs, job_environment_prefix, check_pr_target
  • Simple run_actionlint findings (single-line shell fixes)

Judgment (requires user input):

  • name_exists, step_approved, complex run_actionlint findings

Step 5: Report

Output a summary table per repo:

File Finding Rule Category
... ... ... ...

Include totals: mechanical findings, judgment findings, and repos with no issues.

Inform the user that they can use the workflow-fix skill to apply fixes based on these findings.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill is a read-only audit tool designed to lint GitHub workflows using the Bitwarden-specific 'bwwl' command-line tool. It follows security best practices by explicitly forbidding automatic installation of dependencies and restricting command execution to the specific linter tool via platform-level configuration.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at a11c77b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 7 months ago
What it can do
Reads files Runs commands
All 5 allowed tools
ReadGlobGrepSkillBash(bwwl:*)
  • bitwarden
  • workflow
  • linting
  • ci-cd
  • github-actions
  • read-only
  • audit

README badge

README badge for bitwarden/ai-plugins/workflow-audit

Runs the Bitwarden workflow linter (bwwl) against GitHub Actions workflows in one or more repos and categorizes findings as mechanical (auto-fixable) or judgment (requiring review). Read-only; integrates with the bitwarden-workflow-linter-rules skill to classify violations.

Generated from the current SKILL.md.

Does this skill modify any files?
No. The skill is strictly read-only and only reports findings from the Bitwarden workflow linter (bwwl). It does not create, modify, or delete any files.
What is bwwl and how do I install it?
bwwl is the Bitwarden workflow linter. The skill requires it to be pre-installed and will stop with an error message if the command is not found. Installation is not handled by the skill itself.
Can this skill lint multiple repos at once?
Yes. The skill supports single repo, multiple repos, or a single file/directory scope. For multiple repos, you must provide the base directory where they are cloned.
What does the skill do with the linter findings?
It parses and categorizes findings as either mechanical (auto-fixable, like capitalization or pinned runner issues) or judgment (requiring user input, like approval checks). Results are displayed in a summary table per repo.

Generated from the current SKILL.md. These answers refresh after source changes.