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.
npx agentmods add rules/stackhawk/agent-skills/stackhawk-hawkscan-findingsgit clone --depth 1 https://github.com/stackhawk/agent-skillsWhat 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 | $0.00061 | $0.01476 |
| Opus 5 | $0.00030 | $0.00738 |
| Sonnet 5 | $0.00012 | $0.00295 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
stackhawk-hawkscan-findings scanned grade A with 2 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
"reproduce_curl": "curl -X POST http://localhost:8080/api/users/search -d '{\"q\": \"\\' OR 1=1--\"}'" 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.
"reproduce_curl": "curl -X POST http://localhost:8080/api/users/search -d '{\"q\": \"\\' OR 1=1--\"}'" How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Findings Parsing and Fix Task Reference
Contents
JSON Output Schema (--json-output)
When running with --json-output, HawkScan produces a single pretty-printed JSON
object to stdout. All other output (progress bars, banners, status messages) is
suppressed.
Important: --json-output requires at least HawkScan Dev Release v5.3.41.
Important: --json-output cannot be used with --trace — the CLI will error
with exit code 1 if both are set.
Full Schema
{
"scan": {
"id": "uuid-or-null",
"applicationId": "uuid",
"environment": "Development",
"host": "https://example.com",
"status": "COMPLETED",
"duration": 45,
"platformUrl": "https://app.stackhawk.com/scans/uuid"
},
"findings": [
{
"name": "Cross-Site Scripting",
"severity": "HIGH",
"count": 3,
"cweId": "CWE-79",
"paths": [
{
"path": "/api/users",
"method": "GET",
"status": "NEW"
}
]
}
],
"errors": [
{
"message": "Authentication failed",
"category": "AUTH"
}
],
"warnings": [
"CDN headers detected: [x-cdn-header]"
],
"thresholdResult": "PASS"
}
Field Reference
| Field | Type | Description |
|---|---|---|
scan.id |
string or null | Scan UUID. Null if scan never started (pre-HSTE error) |
scan.applicationId |
string | Application UUID from config |
scan.environment |
string | Environment name (e.g., "Development") |
scan.host |
string | Target URL being scanned |
scan.status |
string | COMPLETED, ERROR, or UNKNOWN |
scan.duration |
int or null | Scan duration in seconds. Null if scan never started |
scan.platformUrl |
string or null | Link to scan results on StackHawk platform |
findings[] |
array | List of detected vulnerabilities. Empty [] if clean |
findings[].name |
string | Alert name (e.g., "SQL Injection") |
findings[].severity |
string | HIGH, MEDIUM, or LOW |
findings[].count |
int | Number of instances found across all paths |
findings[].cweId |
string | CWE identifier (e.g., "CWE-89") |
findings[].paths[] |
array | Affected endpoints |
findings[].paths[].path |
string | Endpoint path (e.g., "/api/users") |
findings[].paths[].method |
string | HTTP method (GET, POST, etc.) |
findings[].paths[].status |
string | Triage status: NEW, FALSE_POSITIVE, RISK_ACCEPTED, or ASSIGNED |
errors[] |
array | Errors during scan. Empty [] if none |
errors[].message |
string | Error description |
errors[].category |
string | Error category: AUTH, CONFIG, UNKNOWN, etc. |
warnings[] |
array of strings | Preflight/runtime warnings. Empty [] if none |
thresholdResult |
string | PASS, FAIL, or UNKNOWN |
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 · 153 lines · 61 tokens per session scan A b6a5a09e167f
stackhawk-hawkscan-findings is a cursor rule published in the GitHub repository stackhawk/agent-skills (16 stars, last pushed 12d ago), licensed MIT. It adds 61 tokens to every session and 1,476 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.