What is stackhawk-api?

A set of instructions for querying StackHawk, a security testing platform, through its command-line tool. It returns security reports, findings, scan history, and app information.

Use it to review security posture, list applications, inspect scan history, view untriaged findings, and manage finding triage.

It gives the agent a defined way to inspect security results and identify findings that need attention without writing custom API requests.

stackhawk-api — Cursor rule by stackhawk

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 rules/stackhawk/agent-skills/stackhawk-api

Clone the repo

git clone --depth 1 https://github.com/stackhawk/agent-skills

Made for: Cursor.

Per session 137 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,364 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00137	$0.02364
Opus 5	$0.00068	$0.01182
Sonnet 5	$0.00027	$0.00473
Haiku 4.5	$0.00014	$0.00236

Measured 2d ago against content hash 5290dd533edd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stackhawk-api 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 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.

Makes network callslowCapability

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

install it and run `hawk init --browser` rather than hand-rolling curl.

cursor/.cursor/rules/stackhawk-api.mdc · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StackHawk API Skill

This skill enables Claude to act as a security reporting agent against the StackHawk platform. The core workflow is:

Question → Authenticate → Query API via hawk op → Present Results → Suggest Next Actions

All platform queries run through the hawk binary's op subtree (hawk op …). It authenticates, refreshes tokens, follows pagination, and emits stable JSON. There is no raw-REST fallback — if hawk is unavailable, install it and run hawk init --browser rather than hand-rolling curl. See references/hawk-op-shortcuts.md.

Step 1: Assess Context

Before making any calls, check what's available:

Is hawk installed and configured? (hawk version reports v6.0.0 or greater)
```
# Identify the driving skill for CLI usage telemetry (read by hawk/hawkop).
export _STACKHAWK_SKILL=api
command -v hawk >/dev/null && hawk op status
```
- valid org + JWT → proceed.
- installed but unconfigured → hawk init --browser (interactive; the combined binary has no hawk op init — hawk init writes ~/.hawk/hawk.properties, which hawk op reads along with the HAWK_API_KEY env var).
- not installed → instruct the user to install the hawk CLI (docs: docs.stackhawk.com) and stop; do not fall back to curl.
Is hawk op authenticated? For local/agentic use, hawk init --browser stores credentials in ~/.hawk/hawk.properties — no env var needed for interactive sessions. Verify:
```
hawk op status
```
CI/CD only: If running in a pipeline, set HAWK_API_KEY as a secret. hawk op reads it directly — no config file required.
Is orgId known? Required for most endpoints.
- hawk op org get returns the active org UUID.
- hawk op org set <ID> switches the default org.

Route based on user intent:

User says...	Go to...
"What's my security posture?" or "dashboard"	Step 3 (org summary)
"Tell me about [app]'s findings" or "what needs attention"	Step 4 (app deep dive)
"What apps haven't been scanned recently?"	Step 3 with stale-app focus
"What changed since last week?" or "what's new"	Step 4 with diff recipe
"Show me untriaged findings"	Step 3, then drill into Step 4 for flagged apps

Read the full file on GitHub · 212 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.

2d ago First seen · 212 lines · 137 tokens per session scan A 5290dd533edd

Subscribe to this mod's changes

stackhawk-api is a cursor rule published in the GitHub repository stackhawk/agent-skills (15 stars, last pushed 12d ago), licensed MIT. It adds 137 tokens to every session and 2,364 once invoked, about $0.0007 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 2026-08-30.

Analytics and metrics Code review Testing

stackhawk-api

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

How it starts

StackHawk API Skill

Step 1: Assess Context

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs