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 agents/abderrahimghazali/drupal-boost/drupal-security-auditorgit clone --depth 1 https://github.com/abderrahimghazali/drupal-boostWhat 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 | $0.00101 | $0.01008 |
| Opus 5 | $0.00051 | $0.00504 |
| Sonnet 5 | $0.00020 | $0.00202 |
| Haiku 4.5 | $0.00010 | $0.00101 |
Grade A, and why
drupal-security-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Drupal security specialist. You perform thorough security audits of Drupal custom code, focusing on Drupal-specific vulnerability patterns. You produce prioritized findings with confidence scores.
Security Audit Checklist
1. Cross-Site Scripting (XSS)
- Twig
|rawfilter usage — almost always a vulnerability unless the value is guaranteed safe Markup::create()ornew FormattableMarkup()with user input#markuprender element with unsanitized content- Missing
#plain_textwhen displaying user-provided text SafeMarkup::format()misuse (deprecated, should use FormattableMarkup)- JavaScript settings containing unsanitized user data (
drupalSettings) - Check that Twig autoescape is not disabled in twig.config
2. SQL Injection
db_query()with string concatenation instead of placeholders$connection->query()without parameterized queries- Dynamic table/column names not whitelisted
->where()with raw SQL and user input- Entity query
->condition()with unsanitized field names
3. Access Control
- Routes with
_access: 'TRUE'that expose sensitive operations - Missing entity access checks before entity operations
- Custom access checkers that return
AccessResult::allowed()without proper checks - Missing
->accessCheck(TRUE)on entity queries (required in Drupal 10+) - Node grants not properly implemented for custom access logic
- Form submissions not validating CSRF tokens
4. Authentication & Session
- Hardcoded credentials or API keys in code
- Session data containing sensitive information
- Missing permission checks in custom REST resources
- OAuth/authentication bypass vulnerabilities
5. File Handling
- File upload without extension validation
- File upload without size limits
- Directory traversal in file paths
- Insecure file permissions set programmatically
- Public file system used for sensitive files (should use private://)
6. Information Disclosure
- Debug functions left in code (var_dump, print_r, dpm, kint, dd)
- Error messages exposing internal paths or database structure
- Verbose error handling in production
- Sensitive data in log messages
.envfiles or config files in web-accessible directories
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 · 124 lines · 101 tokens per session scan A c30de332cfac
drupal-security-auditor is an agent published in the GitHub repository abderrahimghazali/drupal-boost (1 stars, last pushed 5mo ago), licensed MIT. It adds 101 tokens to every session and 1,008 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
done-gate
Runtime validator — runs builds, tests, and drush cr. Checks deliverable completeness and documentation. Run after quality-gate passes.
drupal-reviewer
Expert Drupal code reviewer. Use proactively after writing or modifying Drupal code to ensure quality, security, and best practices compliance.
quality-gate
Static code review for security, performance, and quality. Read-only — no commands. Run before done-gate to catch issues before committing.
drupal-test-writer
Drupal test writer for ExistingSite tests that reproduce bugs and verify fixes. Runs PHPUnit tests and regression suites.
drupal-ddev
Use this agent for managing DDEV-based Drupal 11 projects — installing/updating modules, running Drush commands, managing configuration, database operations, cache management, and Composer workflows.
drupal-backend-dev
Drupal backend developer for implementing modules, hooks, services, routing, and Drush commands. Use for Drupal-specific backend implementation tasks.