agents-at-scale-ark: Skill for Claude Code

.claude/skills/pentest-issue-resolver/SKILL.md

ark-pentest-issue-resolver is a skill for Claude Code from mckinsey/agents-at-scale-ark. It costs 37 tokens per session (6,614 once invoked), scanned B, original, Apache-2.0.

A workflow for resolving common penetration-testing findings and OWASP Top 10 security problems, such as cross-site scripting, SQL injection, and CSRF. It provides patterns for detecting issues and guidance for mitigating them.

In plain words
What is it for?
Use it when a penetration test or security audit reports a common web vulnerability that needs investigation and repair.
Why use it?
It helps turn security audit findings into specific code changes and defenses.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is mckinsey/agents-at-scale-ark's own configuration. It tells Claude Code how to work on agents-at-scale-ark itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents-at-scale-ark configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is with open(f'/var/www/uploads/{filename}', 'r') as f: # Can access ../../../../etc/passwd.

Reuse

Borrowing it

Nothing to install: this file belongs to mckinsey/agents-at-scale-ark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mckinsey/agents-at-scale-ark/main/.claude/skills/pentest-issue-resolver/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mckinsey/agents-at-scale-ark

Made for: Claude Code.

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 ark-pentest-issue-resolver

README.md
[![agentmods](https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/pentest-issue-resolver/github.svg)](https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/pentest-issue-resolver)
Your own site
<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/pentest-issue-resolver"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/pentest-issue-resolver/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 ark-pentest-issue-resolver

Your own site · 80×15
<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/pentest-issue-resolver"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/pentest-issue-resolver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,614 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 4 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 9 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Output Handling · line 72
    Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.
    Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
  • high Anti-Refusal · line 243
    Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.
    Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
  • high Privilege Escalation · line 623
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 949
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Tool Misuse · line 667
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 667
    Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.
    Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
  • high YARA Match · line 667
    YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).
    Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
  • high Tool Misuse · line 671
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Excessive Agency · line 578
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
How audits are shown
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 $0.00037 $0.06614
Opus 5 $0.00018 $0.03307
Sonnet 5 $0.00007 $0.01323
Haiku 4.5 $0.00004 $0.00661

Measured 8d ago against content hash e79594fd7a17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

ark-pentest-issue-resolver scanned grade B with 4 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 8d 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

data = pickle.loads(untrusted_data) # Can execute arbitrary code!

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

os.system(f'ls -l {filename}') # Can inject: file.txt; rm -rf /

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

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

curl -I https://ark-dashboard.example.com | grep -E "X-Frame-Options|X-Content-Type-Options|Strict-Transport-Security"

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

os.system(f'ls -l {filename}') # Can inject: file.txt; rm -rf /
.claude/skills/pentest-issue-resolver/SKILL.md · 1,013 lines

How it starts

The opening of the file, as written. The whole thing — 1,013 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ark Penetration Test Issue Resolver

Provides detection patterns, mitigation strategies, and fixes for common penetration testing issues found in the Ark platform.

When to use this skill

Use this skill when:

  • User reports a penetration testing finding without a specific CVE
  • Security audit reveals OWASP Top 10 vulnerabilities
  • User mentions issues like "XSS", "SQL injection", "CSRF", etc.
  • Need to identify and fix common security misconfigurations

Note: This skill is used by the ark-security-patcher agent when no specific CVE is mentioned. It helps identify and resolve standard penetration testing findings.

Common Penetration Test Issues

1. SQL Injection

Description: Attacker can inject malicious SQL queries through user input.

Detection Patterns:

# VULNERABLE: Direct string concatenation
query = f"SELECT * FROM users WHERE username = '{username}'"

# VULNERABLE: String formatting
query = "SELECT * FROM users WHERE id = %s" % user_id

Mitigation:

# SECURE: Use parameterized queries
cursor.execute("SELECT * FROM users WHERE username = ?", (username,))

# SECURE: Use ORM with parameter binding
User.objects.filter(username=username)

# SECURE: Use sqlalchemy with bound parameters
session.query(User).filter(User.username == username)

Ark Context:

  • Check Python services: services/ark-api/, executor services
  • Search for: cursor.execute, db.query, SQL string concatenation
  • Verify all database queries use parameterized statements

2. Cross-Site Scripting (XSS)

Description: Attacker can inject malicious JavaScript into web pages viewed by other users.

Types:

  • Reflected XSS: Malicious script in URL/request is reflected in response
  • Stored XSS: Malicious script stored in database and displayed to users
  • DOM-based XSS: Vulnerability exists in client-side JavaScript

Detection Patterns:

// VULNERABLE: Direct innerHTML manipulation
element.innerHTML = userInput;

// VULNERABLE: Unescaped template rendering
return `<div>${userInput}</div>`;

// VULNERABLE: dangerouslySetInnerHTML in React
<div dangerouslySetInnerHTML={{__html: userInput}} />

Read the full file on GitHub · 1,013 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. 8d ago First seen · 1,013 lines · 37 tokens per session scan B e79594fd7a17

Subscribe to this mod's changes

ark-pentest-issue-resolver is a skill published in the GitHub repository mckinsey/agents-at-scale-ark (423 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 6,614 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 4 findings (unrestricted tool access, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

container-manager-kubernetes-operations

Full operational Kubernetes surface via the container-manager-mcp MCP server — workloads (pods/rollouts/StatefulSets/DaemonSets/ReplicaSets/Jobs/CronJobs), config (ConfigMaps/Secrets/Namespaces/CRDs/patch), networking (Ingress/native Services/NetworkPolicy/DNS), storage (PV/PVC/StorageClass/snapshots/CSI), RBAC…

Knuckles-Team/container-manager-mcp · 189 tokens

k8s-ops

Opinionated multi-step Kubernetes workflows on top of the k8s-mcp server. Encodes tool-sequencing logic and failure-mode decision trees for deploying from a repo, debugging pods/rollouts, performing safe restarts, and auditing cluster posture. Use when the user asks to deploy, diagnose, restart, roll out, or audit…

jingyanjiang/k8s-mcp · 77 tokens

kubernetes-mesh-provisioner

Kubernetes Mesh Provisioner atomic skill. Stands up an RKE2 cluster (server + agents) with Cilium CNI and the NVIDIA GPU device plugin, the Kubernetes parallel of swarm-mesh-provisioner. Idempotent — re-runnable.

Knuckles-Team/container-manager-mcp · 60 tokens

flow-nexus-platform

Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.

ruvnet/ruflo · 24 tokens

cost-optimization

Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.

wshobson/agents · 48 tokens

network-rca

Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…

kubeshark/kubeshark · 163 tokens