Salesforce Data HandlingSAFE
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
Overview
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
4f83675ca38aOBSERVED · 2026-10-08Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: salesforce-data-handling description: 'Review Salesforce data classification, minimum access, extraction, transformation, retention, subject requests, deletion, legal hold, and evidence. Use when operating privacy-sensitive workflows. Trigger with "review Salesforce data handling".' argument-hint: "[org-alias] [dataset-or-object]" allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit version: 1.8.0 author: Jeremy Longshore <[email protected]> license: MIT tags: [saas, salesforce, privacy, data-governance, retention] model: inherit effort: high compatibility: Designed for Claude Code; personal-data access, export, retention, correction, and deletion require privacy, legal, security, and data-owner approval --- # Salesforce Data Handling and Privacy Operations ## Overview Translate policy and legal obligations into object- and field-level controls without treating one Salesforce feature or object as automatic compliance. ## Prerequisites - Dataset, objects, fields, data subjects, purposes, jurisdictions, systems of record, recipients, and owners - Current object metadata, CRUD and field access, sharing, encryption, retention, audit, export, and deletion capabilities - Privacy policy, legal basis, subject-request process, legal holds, incident process, and evidence requirements ## Tool Discipline Use `Read`, `Glob`, and `Grep` to inspect approved repository and evidence files, `WebFetch` to re-check current first-party Salesforce documentation, and `Write` or `Edit` only for secretless plans, fixtures, configuration, and redacted receipts. ## Current Contract Salesforce provides data, security, privacy, encryption, and metadata capabilities that vary by product and entitlement. The Individual object can support privacy use cases where enabled, but its presence alone does not prove GDPR, CCPA, retention, or subject-request compliance. ## Authentication Use minimum object, field, record, and export access for the approved purpose. Separate administrators, privacy operators, integration principals, and support access; never place tokens or raw personal data in fixtures, logs, or receipts. ## Instructions 1. Map objects and fields to data classes, purposes, legal bases, subjects, sources of truth, recipients, residency, retention, and owners. 2. Discover current metadata, permissions, sharing, encryption, audit, Individual-object or alternative mapping, and downstream copies. 3. Minimize selected fields and rows, parameterize queries, redact logs, encrypt transport and storage, and restrict exports. 4. Define correction, access, portability, restriction, deletion, anonymization, and legal-hold actions across every authoritative and copied system. 5. Use stable case identifiers and approval gates; never assume deleting one Salesforce record satisfies a multi-system request. 6. Test the workflow with synthetic subjects, inaccessible fields, holds, duplicates, relationships, events, backups, and failures. 7. Execute approved cases, reconcile every system and exception, retain minimum evidence, and delete temporary exports on schedule. ## Approval Boundaries Do not export, disclose, correct, merge, anonymize, delete, unencrypt, shorten retention, or override a legal hold without accountable approval. ## Output Return the data map, control and permission evidence, minimum query or export contract, case plan, approvals, system results, exceptions, reconciliation, and expiry. ## Error Handling | Condition | Response | |---|---| | Legal hold conflicts with deletion | Stop deletion and route the case to legal with the held systems identified. | | Field or copy ownership is unknown | Treat completion as unproven until an owner and disposition are established. | | Temporary export exceeds approved scope | Quarantine and securely delete it, assess exposure, and regenerate the minimum dataset. | ## Example A redacted completion receipt might look like this: ```text case=DSR-88; systems=4; fields=approved-minimum; hold=none; actions=completed; exceptions=0; exports=deleted ``` ## Resources - [Salesforce data protection and privacy](https://help.salesforce.com/s/articleView?id=sf.data_protection_and_privacy.htm) - [Individual object reference](https://developer.salesforce.com/docs/atlas.en-us.object_reference.meta/object_reference/sforce_api_objects_individual.htm) ## Next Steps Run the workflow first in the lowest-risk authorized org and preserve its redacted receipt. Schedule a review against the next Salesforce seasonal release and the customer change calendar.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__salesforce-data-handling.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 4f83675ca38a | SAFE | B | 89 | first audit |
Questions
What does the Salesforce Data Handling skill do?
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
Is Salesforce Data Handling safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Salesforce Data Handling access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Salesforce Data Handling work with?
Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.