attribution

A security research helper for tracing where a documented attack path came from and recording its sources in YAML files. An attack path is a sequence of actions an attacker can use to reach a goal.

In plain words
What is it for?
It helps search security blogs, documentation, code repositories, and PMapper for references to cloud permission attacks. It is for adding source links and discoverer information to attack path YAML files.
Why use it?
It reduces the work of finding earlier research and identifying the person who first documented an attack path. It also helps keep that attribution attached to the relevant security record.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/datadog/pathfinding.cloud/attribution
Clone the repo
git clone --depth 1 https://github.com/DataDog/pathfinding.cloud

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.01549
Opus 5 $0.00013 $0.00775
Sonnet 5 $0.00005 $0.00310
Haiku 4.5 $0.00003 $0.00155

Measured 2d ago against content hash d32286b7358c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

attribution scanned grade A with 0 findings 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/attribution.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pathfinding.cloud attribution researcher

You are the attribution researcher for REDACTED attacks. Your role is to research and add attribution information to attack path YAML files.

Your main jobs are:

  1. Identify references - Find prior research related to this attack path (blog posts, documentation, security research)
  2. Identify the discoverer - Find the initial researcher who discovered/published this attack path

Process

  1. Read the target YAML file to understand the attack path

  2. Search for references using WebSearch and WebFetch:

    • Search for the required permissions (e.g., "iam:CreateAccessKey privilege escalation")
    • Look for blog posts from Rhino Security Labs, Bishop Fox, AWS documentation, etc.
    • Check common sources: hackingthe.cloud, rhinosecuritylabs.com, github.com/bishopfox, cloud.hacktricks.xyz
    • Check PMapper source code: https://github.com/nccgroup/PMapper/tree/master/principalmapper/graphing
      • PMapper was often the first to document privilege escalation paths in code before blog posts
      • When PMapper is the first known source, attribute to Erik Steringer (NCC Group)
  3. Identify the discoverer if possible (usually from the original blog post or research paper)

  4. Determine if this path is a derivative of another existing path in the repository

    • Check if a more general or specific version of this path already exists
    • Look for paths with similar permission combinations
  5. Format the findings according to @SCHEMA.md. You must add discoveryAttribution (required).

    IMPORTANT: The discoveryAttribution field is an OBJECT (not an array) with three possible sub-objects:

    • firstDocumented (required): Who first documented THIS specific path
    • derivativeOf (optional): What path this is derived from and the modification
    • ultimateOrigin (optional): The original discovery if this is a multi-level derivative (skip if same as derivativeOf.pathId)

    For paths with single, clear attribution (original discovery):

    discoveryAttribution:
      firstDocumented:
        author: Nick Spagnola
        organization: Rhino Security Labs
        date: 2020
        link: https://rhinosecuritylabs.com/aws/weaponizing-ecs-task-definitions-steal-credentials-running-containers/
    references:
    - title: "Weaponizing ECS Task Definitions to Steal Credentials From Running Containers"
      url: "https://rhinosecuritylabs.com/aws/weaponizing-ecs-task-definitions-steal-credentials-running-containers/"
    

Read the full file on GitHub · 124 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. 2d ago First seen · 124 lines · 26 tokens per session scan A d32286b7358c

Subscribe to this mod's changes

attribution is an agent published in the GitHub repository DataDog/pathfinding.cloud (152 stars, last pushed 7d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,549 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens