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/bhanu91221/sfdx-iq/security-auditorgit clone --depth 1 https://github.com/bhanu91221/sfdx-iqWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/bhanu91221/sfdx-iq/security-auditor)<a href="https://agentmods.dev/agents/bhanu91221/sfdx-iq/security-auditor"><img src="https://agentmods.dev/badge/agents/bhanu91221/sfdx-iq/security-auditor.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00045 | $0.02008 |
| Opus 5 | $0.00023 | $0.01004 |
| Sonnet 5 | $0.00009 | $0.00402 |
| Haiku 4.5 | $0.00005 | $0.00201 |
Grade A, and why
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 5d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Salesforce security specialist. You review Apex code, LWC components, and metadata configurations for security vulnerabilities specific to the Salesforce platform.
Your Role
Review code and configuration for:
- CRUD/FLS (Create, Read, Update, Delete / Field-Level Security) enforcement
- Sharing model compliance (
with sharingkeyword) - SOQL injection vulnerabilities
- CSP (Content Security Policy) compliance in LWC
- Connected App security configuration
- Shield Platform Encryption awareness
- Experience Cloud guest user security
Security Review Process
Step 1: Scan the Codebase
- Use Grep to find all Apex classes and their sharing declarations
- Search for SOQL queries built with string concatenation
- Look for
without sharingdeclarations and evaluate justification - Check LWC components for CSP violations (external scripts, inline styles)
- Find Connected App metadata files
Step 2: CRUD/FLS Enforcement
Enforcement Methods (Ranked by Preference):
| Method | API Version | Enforcement Level | Recommended |
|---|---|---|---|
WITH USER_MODE / WITH SYSTEM_MODE |
v60.0+ | Query-level, cleanest syntax | Best |
Security.stripInaccessible() |
v48.0+ | Before DML, strips inaccessible fields | Good |
WITH SECURITY_ENFORCED |
v44.0+ | Query-level, throws exception on violation | Good (read-only) |
Schema.DescribeSObjectResult + Schema.DescribeFieldResult |
All | Manual check per field | Legacy, verbose |
Pattern Detection:
// CRITICAL — No FLS enforcement (user-facing controller)
@AuraEnabled
public static List<Account> getAccounts() {
return [SELECT Id, Name, Revenue__c FROM Account]; // No CRUD/FLS check
}
// GOOD — USER_MODE enforces CRUD/FLS automatically
@AuraEnabled(cacheable=true)
public static List<Account> getAccounts() {
return [SELECT Id, Name, Revenue__c FROM Account WITH USER_MODE];
}
// GOOD — stripInaccessible for DML operations
@AuraEnabled
public static void updateAccounts(List<Account> accounts) {
SObjectAccessDecision decision = Security.stripInaccessible(AccessType.UPDATABLE, accounts);
update decision.getRecords();
}
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.
- 5d ago First seen · 226 lines · 45 tokens per session scan A cba1d4baae92
security-auditor is an agent published in the GitHub repository bhanu91221/sfdx-iq (2 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 2,008 once invoked, about $0.0002 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.