career-workspace-ambujsystemsCAUTION
Evidence-Grounded Career Workspace & Claim-Validation Engine • Real-Time Company Intelligence • 0% Overclaim Guarantee
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
<img src="https://readme-typing-svg.demolab.com?font=Fira+Code&weight=600&size=20&pause=1000&color=6EE7B7&background=00000000¢er=true&vCenter=true&repeat=true&width=750&height=70&lines=Evidence-Grounded+Generation+%E2%80%A2+Claim+Validation;Tavily+8-Page+Crawl+%2B+Jina+AI+Reader+Markdown+Extractor;Third-Party+%26+Payroll+Detection+via+Verbatim+JD+Quotes;Anthropic+MCP+Server+%2B+Next.js+16+Multi-Stage+Docker" alt="Typing SVG" />
[](https://career-workspace-ambujsystems.vercel.app/) [](https://career-workspace-ambujsystems.vercel.app/docs) [](https://github.com/Ambuj123-lab/career-workspace-ambujsystems/releases/latest) [](https://stats.uptimerobot.com/4tYmSQnuBE?utmsource=statusbadge&utmmedium=referral) [](https://www.producthunt.com/products/covercraft-ai-3) [
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
ats_readiness | read | Perform heuristic ATS compliance checks (keyword coverage, word count, metrics density, parseable formatting). |
company_research | read | Search web for verified company information and engineering culture using Tavily API and grounded synthesis. |
cover_letter_generator | read | Generate an evidence-grounded, structured 3-paragraph cover letter strictly bounded by candidate verified skills. |
evidence_validator | read | Validate factual resume claims against verified web source citations using deterministic Claim Ledger verification. |
github_proofer | read | Audit public GitHub repositories to cross-reference candidate technical resume claims with verified commit history. |
huggingface_proofer | read | Inspect public Hugging Face assets (models, spaces, datasets, downloads) to verify GenAI, LoRA, GGUF, and LLM fine-tuning claims. |
jd_analyzer | read | Parse target Job Description and match required skills against candidate experience with evidence classification. |
source_filter | read | Evaluate domain credibility, tier ranking (Tier 1 vs Noise), and filter outdated news (>18m) or stale tech stack signals. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (6 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (7)
name: covercraft-mcp
import { NextResponse } from "next/server";"use client";
.env.local.example
mcp, google-generativeai, tavily-python, python-dotenv
@google/generative-ai, framer-motion, langfuse, langsmith, mammoth, mongodb, next-auth, pdf-parse
- **Prompt Injection Guardrails:** Heuristic scanning against adversarial prompt injections (`ignore all previous instructions`, `system prompt:`, `bypass`, `<|im_start|>`).
Gates applied: no_behavioural_pass.
a99a865a2f8cfull audit observations/trust-audit/mcp-server/ambuj123-lab__career-workspace-ambujsystems.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | a99a865a2f8c | CAUTION | B | 89 | first audit |
Questions
What is the career-workspace-ambujsystems MCP server?
Evidence-Grounded Career Workspace & Claim-Validation Engine • Real-Time Company Intelligence • 0% Overclaim Guarantee
What tools does career-workspace-ambujsystems expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is career-workspace-ambujsystems safe to connect to an agent?
With care. The audit graded it B (89/100) and found 7 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does career-workspace-ambujsystems need?
It reads GEMINI_API_KEY, GITHUB_TOKEN, GOOGLE_CLIENT_SECRET, HF_TOKEN, JINA_API_KEY, LANGCHAIN_API_KEY, LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, OPENROUTER_API_KEY and TAVILY_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does career-workspace-ambujsystems run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as web at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (a99a865a2f8c), read on 2026-10-11. The repository is watched and re-audited when it changes.