hawkscan

A security-testing workflow that checks a running web application or API for vulnerabilities, then helps address every reported issue and checks again.

In plain words
What is it for?
Use it to configure and run HawkScan, review its findings, create fix tasks, and rescan the application.
Why use it?
It gives coding agents a repeatable way to find security problems and verify that fixes worked, including issues outside the latest code changes.

Skill for Claude CodeCodex

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/stackhawk/agent-skills/hawkscan
Any agent
npx skills add stackhawk/agent-skills --skill hawkscan
Clone the repo
git clone --depth 1 https://github.com/stackhawk/agent-skills

Made for: Claude Code, Codex.

Per session 217 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,743 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 $0.00217 $0.06743
Opus 5 $0.00109 $0.03372
Sonnet 5 $0.00043 $0.01349
Haiku 4.5 $0.00022 $0.00674

Measured 2d ago against content hash 60718eacd7b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hawkscan 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.

plugins/hawkscan/skills/hawkscan/SKILL.md · 511 lines

How it starts

The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HawkScan Skill

This skill enables Claude to act as the security testing orchestrator in an agentic coding loop. The core workflow is:

Code changes → Start Application/API → Configure HawkScan → Run scan → Parse findings → Generate fix tasks → Repeat


Prerequisites (preflight — run before anything else)

This skill requires hawk v6.0.0 or newer. Verify:

hawk version
hawk config --help >/dev/null 2>&1 || echo "MISSING: hawk config — upgrade hawk to v6.0.0+"
hawk skills status

If hawk is older than 6.0.0 or hawk config --help fails, stop and tell the user to upgrade before proceeding. Do not inline auth recipes from memory — they live in hawk config show and are stale by design when hardcoded.

hawk skills status reports whether the installed StackHawk agent skills are current. If it lists anything out of date, surface the exact upgrade command it prints (e.g. /plugin marketplace update stackhawk && /plugin update hawkscan) and recommend the user update before continuing — a stale skill may be missing fixes for the very issues you'll hit. It's a recommendation, not a hard stop: proceed if the user prefers. (If the subcommand isn't recognized, the installed hawk predates it — skip this check.)

See references/installation.md for upgrade and install instructions.


Companion Skills

The api skill wraps read-only StackHawk platform lookups via the hawk CLI (hawk op …):

Purpose Command
Check if App exists hawk op app list --format json
Check if Env exists hawk op env list --app <NAME|UUID> --format json
Get findings with triage hawk op scan get --app <NAME|UUID> --detail full --format json
List ASM repos hawk op repo list --format json
Link app to ASM repo hawk op repo link --repo-id <ID> --app-id <ID>
Get tech flags hawk op app tech-flags get --app <NAME|UUID> --format json
Disable all tech flags hawk op app tech-flags disable-all --app <NAME|UUID> --yes
Set specific tech flags hawk op app tech-flags set --app <NAME|UUID> Key=true
Triage a finding hawk op scan triage --scan <ID> --hash <HASH> --status false-positive --note ""
Bulk triage from file hawk op scan triage --scan <ID> --from-file triage.yaml
Annotate w/o triage perm hawk op finding note --scan <ID> --hash <HASH> --note "..."
Get scanned URIs hawk op scan uris <scanId> --format json (skip if the subcommand errors)
Get effective scan config hawk op scan config <scanId> (skip if the subcommand errors)

Read the full file on GitHub · 511 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 · 511 lines · 217 tokens per session scan A 60718eacd7b5

Subscribe to this mod's changes

hawkscan is a skill published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 12d ago), licensed MIT. It adds 217 tokens to every session and 6,743 once invoked, about $0.0011 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens