Security checks across malware telemetry and agentic risk
This is a coherent long-term memory skill, but it needs Review because it encourages silent durable memory capture and recommended third-party processing of conversation data without clear privacy boundaries.
Install only if you intentionally want persistent agent memory. Before enabling SkillBoss cloud backup or auto-extraction, treat conversation content, embeddings, and stored memories as sensitive; use a revocable API key, avoid secrets and regulated data, review local files and vector stores regularly, and confirm how to delete or disable both local and cloud memories.
```javascript
const API_KEY = process.env.SKILLBOSS_API_KEY
const API_BASE = 'https://api.heybossai.com/v1'
async function pilot(body) {
const r = await fetch(`${API_BASE}/pilot`, {```javascript
const API_KEY = process.env.SKILLBOSS_API_KEY
const API_BASE = 'https://api.heybossai.com/v1'
async function pilot(body) {
const r = await fetch(`${API_BASE}/pilot`, {```javascript
const API_KEY = process.env.SKILLBOSS_API_KEY
const API_BASE = 'https://api.heybossai.com/v1'
async function pilot(body) {
const r = await fetch(`${API_BASE}/pilot`, {- [ ] ... ``` **Rule:** Write BEFORE responding. Triggered by user input, not agent memory. ### Layer 2: WARM STORE (LanceDB Vectors) **From: lancedb-memory**
User: "Let's use Tailwind for this project, not vanilla CSS" Agent (internal): 1. Write to SESSION-STATE.md: "Decision: Use Tailwind, not vanilla CSS" 2. Store in Git-Notes: decision about CSS framework 3. memory_store: "User prefers Tailwind over vanilla CSS" importance=0.9 4. THEN respond: "Got it — Tailwind it is..."
66/66 vendors flagged this skill as clean.