Salesforce API Integration

• Outcome: Review
• Latest audit: Jul 27, 2026 · 10:04 AM UTC
• Version: 1.0.3

Overview

This skill is a disclosed Salesforce API helper with local note storage and safety gates for destructive Salesforce actions.

Install only if you want an agent to work with Salesforce APIs using your Salesforce credentials. Keep the integration user's permissions narrow, review the local Clawic notes because they may contain org IDs, job IDs, schema, contacts, and business context, and require sandbox rehearsal plus explicit confirmation before production deletes, hard deletes, mass updates, or metadata deploys.

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Context-Inappropriate Capability

Medium

• Confidence: 91% confidence
• Finding: The documentation explicitly instructs the agent to write operational Salesforce data, including job metadata, failure causes, and potentially record identifiers, into local files under `~/Clawic/data/...`. That behavior extends beyond the stated API-integration scope and can create an ungoverned local datastore containing sensitive business data, which may bypass retention, access-control, and data-handling requirements.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The template instructs the agent to delete content from `memory.md` during split operations without requiring an explicit user-facing warning or confirmation for that destructive action. Although the deletion is intended as housekeeping, automated file modification in a memory system can still cause loss of context, auditability gaps, or accidental removal of important user data if the split logic is triggered incorrectly.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: This skill gives concrete create, update, upsert, and delete instructions for live Salesforce records, including destructive operations and bypass headers, but lacks a prominent general warning that these actions can alter or remove production data. In an agent setting, that omission increases the chance of unsafe execution against production orgs, especially because the document emphasizes operational success and retry behavior more than environment verification and user confirmation.

Session Persistence

Medium

• Category: Rogue Agent

Content

Everything except artifacts, per-object schema files, load records and the shared boxes begins inside `memory.md`. Splitting is a procedure, not a suggestion:

1. **Who and when**: the agent about to append counts the section's entries **before** adding the one that would cross the line.
2. **Threshold**: past **~15 entries or ~40 lines of real content** — scaffolding, headings and comments do not count, and in tables the entry count rules — then, in the same turn: create the new file in `~/Clawic/data/salesforce-api-integration/`, move the whole section into it, **delete the section from `memory.md`**, add its line to `## Boxes`, and append the new entry to the new file.
3. **Identical headings on both sides** of the move, so the split is a copy-paste and never a rewrite.
4. **Precedence**: never leave a copy behind. If the same data ever appears in both places, the extracted file wins and the `memory.md` copy is deleted.

• Confidence: 82% confidence
• Finding: The split procedure persists session-derived information into long-lived files and directs the agent to remove the original copy afterward. While meant to organize memory, this creates a risk of unintended persistence and opaque state transitions, especially if sensitive or stale information is moved automatically between files without strong validation and retention controls.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: memory-template.md:61