Auditing External Claude Plugins

What it does

When your agent uses it

• Asked to audit an external plugin
• Audit a vendored plugin
• Run a plugin security audit
• Updated external plugin pin needs a pre-merge security review

Example prompts

• “audit an external plugin”
• “audit a vendored plugin”
• “run a plugin security audit”
• “/auditing-external-claude-plugins”

Requirements

• A Bash shell
• Pre-approved tools (allowed-tools): Bash(${CLAUDE_SKILL_DIR}/scripts/gather-evidence.sh *), Bash(${CLAUDE_SKILL_DIR}/scripts/beautify.sh *), Bash(grep *), Bash(jq *), Bash(file *), Bash(go version *), Bash(strings *), Bash(shasum *), Read, Write, Skill

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Run ${CLAUDE_SKILL_DIR}/scripts/gather-evidence.sh $plugin-repo-url $commit-sha. It ends with an inventory of what it gathered…
2. 2Invoke Skill(bitwarden-security-context), Skill(detecting-secrets), Skill(analyzing-code-security), and Skill(reviewing-dependencies) to…
3. 3Audit each of the following. Two are required regardless of what else is found; resolve each to a numbered finding or an explicit clean…
4. 4Resolve OUTPUT_FILE: use $output-file if given, otherwise ${CLAUDE_PLUGIN_DATA}/plugin-audits/{plugin}-{short-sha}-{date}.md, where…
5. 5Write the report to OUTPUT_FILE using this exact structure. Every section is required, in this order
6. 6Confirm OUTPUT_FILE as your final line. Do not post to GitHub or run any gh pr comment/gh api mutation.

What it can do on your machine

Read from SKILL.md and the folder at commit 53e22a3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash(${CLAUDE_SKILL_DIR}/scripts/gather-evidence.sh *)
  • Bash(${CLAUDE_SKILL_DIR}/scripts/beautify.sh *)
  • Bash(grep *)
  • Bash(jq *)
  • Bash(file *)
  • Bash(go version *)
  • Bash(strings *)
  • Bash(shasum *)
  • Read
  • Write

  …and 1 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 4 files in scripts/ (Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • gh
  • go

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Auditing External Claude Plugins loads about 1.8k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 618 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~98

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 618 words (~1,752 tokens).

name

auditing-external-claude-plugins

allowed-tools

Bash(${CLAUDE_SKILL_DIR}/scripts/gather-evidence.sh *), Bash(${CLAUDE_SKILL_DIR}/scripts/beautify.sh *), Bash(grep *), Bash(jq *), Bash(file *), Bash(go version *), Bash(strings *), Bash(shasum *), Read, Write, Skill

argument-hint

<plugin-repo-url> <commit-sha> [output-file]

arguments

plugin-repo-url, commit-sha, output-file

context

fork

agent

bitwarden-security-engineer:bitwarden-security-engineer

model

fable

background

false

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (scripts) in plugins/bitwarden-security-engineer/skills/auditing-external-claude-plugins of bitwarden/ai-plugins.

• SKILL.md
• scripts/beautify.sh
• scripts/gather-evidence.sh
• scripts/package-lock.json
• scripts/package.json

Open the folder on GitHubat commit 53e22a3