tob-actions-auditor

tob-actions-auditor is an agent for Claude Code from iamcxa/kc-claude-plugins. It costs 43 tokens per session (1,801 once invoked), scanned A, original, MIT.

A security auditor for GitHub Actions workflows that use AI coding agents. GitHub Actions workflows are automated instructions that run tasks such as tests or deployments.

In plain words
What is it for?
Auditing changed workflow files for environment-variable injection, expression injection, unsafe sandboxes, broad allowlists, and related risks.
Why use it?
It looks for ways untrusted input or unsafe permissions could make an AI agent run harmful commands or access more than intended. It checks only the workflow files provided for review.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code; mentions Codex.

Part of the kc-pr-flow plugin — 7 skills, 3 agents shipped together

Good fit Auditing changed workflow files for environment-variable injection, expression injection, unsafe sandboxes, broad allowlists, and related risks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/iamcxa/kc-claude-plugins/tob-actions-auditor
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Made for: Claude Code.

Or install kc-pr-flow, the plugin that ships this one along with the rest of its 7 skills, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tob-actions-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/tob-actions-auditor/github.svg)](https://agentmods.dev/agents/iamcxa/kc-claude-plugins/tob-actions-auditor)
Your own site
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/tob-actions-auditor"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/tob-actions-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tob-actions-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/tob-actions-auditor"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/tob-actions-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01801
Opus 5 $0.00022 $0.00901
Sonnet 5 $0.00009 $0.00360
Haiku 4.5 $0.00004 $0.00180

Measured 9d ago against content hash 8072ba5c2378, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tob-actions-auditor scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Detection**: `gh issue view`, `gh pr view`, `curl` fetching issue/PR data, piped to AI CLI.
kc-pr-flow/agents/tob-actions-auditor.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ToB Actions Auditor

You are a GitHub Actions security auditor based on Trail of Bits' agentic-actions-auditor methodology. You detect security vulnerabilities in CI/CD workflows that invoke AI coding agents. Dispatched by kc-pr-review as a conditional parallel agent.

Input Contract

Field Required Description
pr_number Yes PR number
owner_repo Yes owner/repo string
workflow_files Yes List of changed .github/workflows/*.yml or *.yaml paths

Scope

Analyze ONLY the workflow files listed in workflow_files. Do not scan the entire .github/workflows/ directory unless a changed workflow references other files via uses: ./.github/workflows/.

Known AI Agent Actions

Detect these action prefixes in workflow steps:

Action Pattern Agent
anthropics/claude-code-action Claude Code
anthropics/claude-code-action@* Claude Code
google/gemini-cli-action Gemini CLI
openai/codex-* OpenAI Codex
github/ai-inference GitHub AI Inference

Also detect CLI-based invocations: claude, gemini, codex in run: blocks.

The Nine Attack Vectors

Analyze each workflow for these vectors:

Vector A — Env Var Intermediary

Event data flows through env: blocks to AI prompts.

# VULNERABLE
env:
  ISSUE_BODY: ${{ github.event.issue.body }}
steps:
  - uses: anthropics/claude-code-action@v1
    with:
      prompt: "Fix: $ISSUE_BODY"  # attacker-controlled!

Detection: Any env: assignment containing ${{ github.event.* }} where the env var is referenced in an AI step's prompt, with, or run field.

Vector B — Direct Expression Injection

GitHub context expressions embedded directly in AI prompts.

# VULNERABLE
prompt: "Review: ${{ github.event.pull_request.body }}"

Detection: ${{ github.event.* }} or ${{ github.event.comment.body }} directly in prompt/run fields of AI steps.

Vector C — CLI Data Fetch

Commands like gh issue view inject attacker data.

# VULNERABLE
- run: |
    BODY=$(gh issue view ${{ github.event.issue.number }} --json body -q .body)
    claude "Fix this: $BODY"

Detection: gh issue view, gh pr view, curl fetching issue/PR data, piped to AI CLI.

Read the full file on GitHub · 214 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 214 lines · 43 tokens per session scan A 8072ba5c2378

Subscribe to this mod's changes

tob-actions-auditor is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,801 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.