stackhawk-api-recipes

A set of ready-made command recipes for StackHawk, a service that scans web applications for security problems. The recipes use StackHawk's command-line API tools to summarize findings and compare scans.

In plain words
What is it for?
Use it to create organization-wide security summaries, inspect an application's scans and alerts, find applications with outdated scans, and see what changed between scans.
Why use it?
It removes the need to assemble separate commands when checking the security status of several applications or investigating scan results.

Cursor rule for Cursor

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-recipes
Clone the repo
git clone --depth 1 https://github.com/stackhawk/agent-skills

Made for: Cursor.

Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,517 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 $0.00077 $0.03517
Opus 5 $0.00039 $0.01758
Sonnet 5 $0.00015 $0.00703
Haiku 4.5 $0.00008 $0.00352

Measured 2d ago against content hash c70233af1dc5, 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-recipes 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.

cursor/.cursor/rules/stackhawk-api-recipes.mdc · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StackHawk API Reporting Recipes

Pre-built compositions for common security reporting questions using hawk op. Run hawk op status first to confirm authentication; set HAWK_API_KEY for CI/CD pipelines.

Setup (run once per shell session for CI/CD):

export HAWK_API_KEY="hawk.xxxxxxxxxxxx"   # from app.stackhawk.com → Settings → API Keys

Recipe 1: Org Security Posture

Question: Across all my apps, what is the current security situation?

What it produces: One row per app showing latest-scan finding counts by severity, sorted by High findings descending.

Step 1 — Fetch all apps and recent scans

apps=$(hawk op app list --format json)
scans=$(hawk op scan list --limit 500 --format json)

Step 2 — Build the posture table

# Join latest scan per app to get severity counts
printf '%s\n%s' "${apps}" "${scans}" | jq -rs '
  .[0] as $apps | .[1] as $scans |

  # Build app name lookup: applicationId -> name
  ($apps.data | map({(.id): .name}) | add // {}) as $names |

  # Find latest completed scan per app
  ($scans.data
    | group_by(.applicationId)
    | map(
        sort_by(.startedTimestamp) | reverse |
        map(select(.status == "COMPLETED")) | .[0]
      )
    | map(select(. != null))
  ) as $latest |

  # Output sorted by High desc
  ($latest | sort_by(.highAlertCount // 0 | . * -1))
  | ["APP", "ENVIRONMENT", "HIGH", "MEDIUM", "LOW", "LAST_SCAN"],
    (.[] | [
      ($names[.applicationId] // .applicationId),
      (.environmentName // "—"),
      (.highAlertCount   // 0 | tostring),
      (.mediumAlertCount // 0 | tostring),
      (.lowAlertCount    // 0 | tostring),
      (.startedTimestamp // "never")
    ])
  | @tsv
' | column -t -s $'\t'

Output format

APP            ENVIRONMENT   HIGH  MEDIUM  LOW  LAST_SCAN
payment-api    Production    5     12      8    2024-01-15T10:30:00Z
auth-service   Staging       3     4       1    2024-01-10T09:00:00Z
admin-portal   Development   0     0       0    2023-11-01T08:00:00Z

Read the full file on GitHub · 400 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 · 400 lines · 77 tokens per session scan A c70233af1dc5

Subscribe to this mod's changes

stackhawk-api-recipes is a cursor rule published in the GitHub repository stackhawk/agent-skills (15 stars, last pushed 12d ago), licensed MIT. It adds 77 tokens to every session and 3,517 once invoked, about $0.0004 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.