sf-security

sf-security is a skill for Claude Code from Clientell-Ai/salesforce-skills. It costs 100 tokens per session (1,675 once invoked), scanned A, original, Apache-2.0.

A security review guide for Salesforce Apex code, the programming language used to build Salesforce server-side logic. It checks access controls, data exposure, sharing settings, and unsafe query construction.

In plain words
What is it for?
Auditing CRUD and field-level permissions, checking sharing declarations, finding SOQL injection risks, enforcing user-mode queries, and detecting possible personal-data exposure.
Why use it?
It helps find issues that could expose records, ignore a user’s permissions, or cause an AppExchange security review failure. It scans for common security mistakes across a codebase.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Good fit Auditing CRUD and field-level permissions, checking sharing declarations, finding SOQL injection risks, enforcing user-mode queries, and detecting possible personal-data exposure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/clientell-ai/salesforce-skills/sf-security
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.

Any agent
npx skills add Clientell-Ai/salesforce-skills --skill sf-security
Clone the repo
git clone --depth 1 https://github.com/Clientell-Ai/salesforce-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for sf-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-security/github.svg)](https://agentmods.dev/skills/clientell-ai/salesforce-skills/sf-security)
Your own site
<a href="https://agentmods.dev/skills/clientell-ai/salesforce-skills/sf-security"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-security/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sf-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/clientell-ai/salesforce-skills/sf-security"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00100 $0.01675
Opus 5 $0.00050 $0.00838
Sonnet 5 $0.00020 $0.00335
Haiku 4.5 $0.00010 $0.00168

Measured 10d ago against content hash aa6d4fa590c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sf-security 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/security-scan.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/sf-security/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Salesforce Security Auditor

You are a Salesforce security specialist. Audit code for the vulnerabilities that cause AppExchange security review failures.

Critical Violations to Detect

1. Missing CRUD/FLS Enforcement

Scan for DML operations without Security.stripInaccessible():

// VIOLATION
insert records;

// COMPLIANT
SObjectAccessDecision decision = Security.stripInaccessible(AccessType.CREATABLE, records);
insert decision.getRecords();

Search patterns:

  • insert / update / delete / upsert without preceding stripInaccessible
  • Database.insert / Database.update without AccessLevel.USER_MODE

2. Missing WITH USER_MODE in SOQL

Scan for SOQL queries without WITH USER_MODE:

// VIOLATION
[SELECT Id FROM Account WHERE Name = :name]

// COMPLIANT
[SELECT Id FROM Account WHERE Name = :name WITH USER_MODE]

3. Missing with sharing

All classes should declare sharing model explicitly:

// VIOLATION
public class MyClass { }

// COMPLIANT
public with sharing class MyClass { }

Only use without sharing when explicitly needed (e.g., running aggregate queries for dashboard data) and document the reason.

4. SOQL Injection

Scan for string concatenation in dynamic SOQL:

// VIOLATION — injection risk
String query = 'SELECT Id FROM Account WHERE Name = \'' + userInput + '\'';

// COMPLIANT — use bind variable
String query = 'SELECT Id FROM Account WHERE Name = :userInput';

// COMPLIANT — use escapeSingleQuotes for truly dynamic queries
String safeName = String.escapeSingleQuotes(userInput);

5. PII/Sensitive Data in Debug Logs

Scan for debug statements that might expose sensitive data:

// VIOLATION
System.debug('User SSN: ' + contact.SSN__c);
System.debug('Credit Card: ' + payment.CardNumber__c);
System.debug(JSON.serialize(sensitiveRecord));

// COMPLIANT — debug ID only
System.debug('Processing contact: ' + contact.Id);

6. Hardcoded Credentials

Scan for:

  • Hardcoded URLs, API keys, passwords, tokens
  • Credentials in string literals instead of Named Credentials or Custom Metadata

Read the full file on GitHub · 196 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 196 lines · 100 tokens per session scan A aa6d4fa590c8

Subscribe to this mod's changes

sf-security is a skill published in the GitHub repository Clientell-Ai/salesforce-skills (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,675 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 2026-08-30.