cross-attack-chains

cross-attack-chains is a skill for Claude Code, Codex from uphiago/recon-skills. It costs 23 tokens per session (969 once invoked), scanned A, original, MIT.

A method for checking whether several verified security findings combine into one authorized attack path. Each step must provide something needed by the next step.

In plain words
What is it for?
Use it to document compound security risks, test approved attack chains safely, and separate proven impact from inferred impact.
Why use it?
It prevents separate findings from being presented as a single compromise without evidence that they connect. It also records when a possible next step has not been tested.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

Recon Skills is a pack of security-testing skills covering reconnaissance, web applications, APIs, authentication, vulnerability validation, cloud infrastructure, and reporting. Security professionals use it for authorized assessments of systems they own or have written permission to test. The catalogue entries are individual skills from the pack.

uphiago/recon-skills · 1,228 stars · on GitHub · hiago.sh

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 skills/uphiago/recon-skills/cross-attack-chains
Any agent
npx skills add uphiago/recon-skills --skill cross-attack-chains
Clone the repo
git clone --depth 1 https://github.com/uphiago/recon-skills

Made for: Claude Code, Codex.

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 cross-attack-chains

README.md
[![agentmods](https://agentmods.dev/badge/skills/uphiago/recon-skills/cross-attack-chains.svg)](https://agentmods.dev/skills/uphiago/recon-skills/cross-attack-chains)
Your own site
<a href="https://agentmods.dev/skills/uphiago/recon-skills/cross-attack-chains"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/cross-attack-chains.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 969 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 5.1 $0.00023 $0.00969
Opus 5 $0.00012 $0.00485
Sonnet 5 $0.00005 $0.00194
Haiku 4.5 $0.00002 $0.00097

Measured 6d ago against content hash f6adf4791c6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cross-attack-chains 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 6d 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.

chains/cross-attack-chains/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Attack Chains

An attack chain is a sequence of verified security behaviors in which each step provides a prerequisite for the next. Several findings on the same target do not form a chain unless the dependency between them is demonstrated.

When to Use

  • Two or more validated findings affect the same trust boundary.
  • One finding exposes an identity, token, route, host, or capability needed by another.
  • A report needs to distinguish standalone impact from compound impact.
  • The next chain step cannot be tested safely and must be labeled inferred.

Prerequisites

  • Captured evidence and negative controls for every component finding.
  • Current authorization for the compound test and any increased side effects.
  • Approved identities, synthetic records, callbacks, and cleanup procedure.
  • A clear stop condition for sensitive data, availability, or scope changes.

How to Run

Create a chain record beneath the target output directory:

TARGET_ID="example-test"
OUTPUT_DIR="${OUTPUT_DIR:-./output}"
CHAIN_DIR="$OUTPUT_DIR/$TARGET_ID/chains"

mkdir -p "$CHAIN_DIR"
touch "$CHAIN_DIR/EXPLOIT_CHAINS.md"

Use evidence states consistently:

State Meaning
Observed Present in captured output
Confirmed Security impact reproduced with a control
Inferred Plausible dependency that has not been tested
Not tested Excluded by scope, safety, or missing prerequisites

Procedure

1. Normalize Component Findings

For each component, record:

  • expected and observed behavior;
  • target, identity, and timestamp;
  • positive evidence and negative control;
  • side effects and cleanup;
  • demonstrated impact;
  • assumptions and testing limits.

Discard scanner labels and version-only leads that have not passed their owning skill's verification.

2. Draw the Dependency

Finding A
  output: approved user identifier
  enables: object lookup in Finding B

Finding B
  output: unauthorized synthetic object read
  enables: none

Read the full file on GitHub · 145 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 145 lines · 23 tokens per session scan A f6adf4791c6c

Subscribe to this mod's changes

cross-attack-chains is a skill published in the GitHub repository uphiago/recon-skills (1,228 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 969 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 skills, from other repositories

performing-cloud-asset-inventory-with-cartography

Perform comprehensive cloud asset inventory and relationship mapping using Cartography to build a Neo4j security graph of infrastructure assets, IAM permissions, and attack paths across AWS, GCP, and Azure.

xalgorix/xalgorix · 49 tokens

detecting-compromised-cloud-credentials

Detecting compromised cloud credentials across AWS, Azure, and GCP by analyzing anomalous API activity, impossible travel patterns, unauthorized resource provisioning, and credential abuse indicators using GuardDuty, Defender for Identity, and SCC Event Threat Detection.

xalgorix/xalgorix · 55 tokens

implementing-aws-config-rules-for-compliance

Implementing AWS Config rules for continuous compliance monitoring of AWS resources, deploying managed and custom rules aligned to CIS and PCI DSS frameworks, configuring automatic remediation with SSM Automation, and aggregating compliance data across accounts.

xalgorix/xalgorix · 53 tokens

implementing-cloud-dlp-for-data-protection

Implementing Cloud Data Loss Prevention (DLP) using Amazon Macie, Azure Information Protection, and Google Cloud DLP API to discover, classify, and protect sensitive data across cloud storage, databases, and data pipelines.

xalgorix/xalgorix · 54 tokens

implementing-cloud-trail-log-analysis

Implementing AWS CloudTrail log analysis for security monitoring, threat detection, and forensic investigation using Athena, CloudWatch Logs Insights, and SIEM integration to identify unauthorized access, privilege escalation, and suspicious API activity.

xalgorix/xalgorix · 50 tokens

implementing-zero-trust-network-access

Implementing Zero Trust Network Access (ZTNA) in cloud environments by configuring identity-aware proxies, micro-segmentation, continuous verification with conditional access policies, and replacing traditional VPN-based access with BeyondCorp-style architectures across AWS, Azure, and GCP.

xalgorix/xalgorix · 59 tokens