More screenshots
Works with the AI Agents you already use
job scam red-flag scorer
Score job postings, offer emails and recruiter texts for known job-scam patterns: fake checks, buy-your-own-equipment, chat-only interviews, upfront fees, task scams, early SSN/bank requests and too-good pay.
$9.99
About this skill
Fake job offers are built to look normal for about two messages. This catches the third.
Paste or save a job posting, offer email (.eml), recruiter text or HTML page and run it. The scorer checks about 17 scam patterns drawn from FTC and state attorney-general warnings: deposit-this-check and overpayment schemes, buying equipment from 'our approved vendor', training or background-check fees, gift cards, crypto and Zelle, reshipping and 'payment processing' jobs, Telegram/WhatsApp interviews, hired-without-interview offers, SSN, bank or ID requests before an offer, task/'app optimization' scams, MLM pitches, urgency and free-mail recruiters. It also flags pay that's too high for an entry-level role and email domains that don't match the company. Each red flag quotes the exact text it found and says what to do. You get a 0-100 risk score, a plain verdict and next steps, including where to report.
What it does
- 17 red-flag rules with quoted evidence and advice for each
- Pay sanity check: annualizes $/hr, /day, /week and /month and flags high pay for no-experience roles
- Sender checks: free-mail recruiters and domains that don't match --company-domain
- Reassuring signs too: a real interview process, a pay range, an employer ATS link
- Batch mode over a folder, a one-line --brief table, JSON, and --fail-at exit code
- Reads .txt, .md, .html and .eml (headers included)
Who it's for
Job seekers, especially for remote, entry-level and IT roles, plus career coaches, college career centers and anyone who helps a family member job-hunt.
Limits
Pattern-based: new scam scripts can slip through, and a real posting can trip a rule. English text only. It reads what you give it and does not verify companies online.
Heuristic screening, not legal advice. A low score does not prove a job or recruiter is real: verify with the employer through contact details you look up yourself.
What's included
SKILL.md: workflow, commands, how to explain resultsscripts/: the tool (standard-library Python)references/: sourcesexamples/: sample inputs used in the demo (all made up)tests/: unit tests (Python 3.8 / 3.9 / 3.13)
Standard-library Python only. No API keys, no network calls, no installs.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
- Pattern-based: new scam scripts can slip through, and a real posting can trip a rule.
- English text only. It reads what you give it and does not verify companies online.
- Heuristic screening, not legal advice. A low score does not prove a job or recruiter is real: verify with the employer through contact details you look up yourself.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
Permissions
File Scopes
Fully offline. No network calls, no credential access, and it never logs into, scrapes or submits anything on job boards.