PromptArmor
promptarmor.com
Actively hiring
Threat Intelligence
Security Compliance
AI Governance & Compliance
Follow
Overview
News
Technologies
Salaries
Products
People
Growth
Offices
Financials
Funding and backers
Team
11-50
employees, estimated range
Hiring now
1
open roles
Backers
1
Y Combinator
Momentum
15/100
in the news
Last sign of life
this month
a posting or a news item
The story so fareach stage dated by its source: the company's releases, the press, registers, filings
Aug 5
On the Hacker News front page Atlassian Rovo Exfiltrates Data, Bypassing Controls · 306 points
May 31
On the Hacker News front page ChatGPT for Google Sheets exfiltrates workbooks · 324 points
Mar 18
On the Hacker News front page Snowflake AI Escapes Sandbox and Executes Malware · 269 points
Jan 14
On the Hacker News front page Claude Cowork exfiltrates files · 870 points
Nov 25, 2025
On the Hacker News front page Google Antigravity exfiltrates data via indirect prompt injection attack · 768 points
Apr 17, 2025
Launched PromptArmor Launches to Help Assess, Monitor Third-Party AI Risks · darkreading.com
Jan 2024
Went through Y Combinator
Dec 2023
Website went live first capture in the Wayback Machine
Tractionpublic signals, read monthly
Web presence
top 0.43%
of 133.2M domains by links, Common Crawl
Hacker News stories
42
best: 870 points
Backed byfrom the funds' portfolios and accelerator catalogs
Y Combinator Investors in similar startupsfunds that back the companies most like this one
Similar startupsby what they do, their industry and backers
Drata is an American security and compliance automation company founded in 2020 that continuously monitors a company's systems and collects…
Responsible Cyber builds governance, risk and third-party management software with its RiskImmune platform. It also runs security advisory…
UpGuard is a cybersecurity company that provides third-party risk management and attack surface management software. Its platform scans…
Coverbase is agentic third party risk management software that tunes AI to your controls and monitors every vendor continuously. Book a…
Agentic Security & Compliance Platform. Save hours on compliance work with AI. Our AI agents monitor controls, manage third parties, govern…
Sprinto is a compliance automation company founded in 2020 that helps cloud-based businesses achieve and maintain security certifications…
Overview
PromptArmor is a San Francisco security startup that monitors the AI-related risk of third-party vendors. Its platform analyses how suppliers use AI models and agents, tracks emerging threats such as prompt injection and data exfiltration, and gives security and compliance teams continuous risk assessments. The company is backed by Y Combinator and is headquartered in San Francisco, California, United States.
News
Anthropic's Skill Scanner Defeated by Backdoored Skills
Anthropic's Skill scanning feature fails to catch backdoored Skills that execute arbitrary attacker-controlled code when run.
Read more
Report
Copilot Cowork Sandbox Bypass Gives Attackers Remote Control
A sandbox bypass in Microsoft Copilot Cowork let a malicious Skill read commands from an attacker's server and send back any data the agent could reach, including Outlook mail, SharePoint files, and chat history.
Read more
Report
Atlassian Rovo Exfiltrates Data, Bypassing Controls
Atlassian AI 'Rovo' is susceptible to zero-click data exfiltration via indirect prompt injection, bypassing organization-level web search controls.
Read more
Report
Claude and ChatGPT Connectors Change Every 9 Minutes
We tracked ChatGPT and Claude connectors for 6 weeks and found that a connector changes every nine minutes: gaining write access, widening its permissions, modifying its toolset, and more.
Read more
Report
Codex 'Auto-review' Agent Runs Malware
Malware risks from agent-based command approval modes, demonstrated on OpenAI Codex.
Read more
Report
Claude Dynamic Workflows Inaccurate Permissions Docs
Claude Dynamic Workflow subagents can execute with elevated permissions violating documented guarantees.
Read more
Report
Ollama Vulnerabilities: Phishing Overlays and Data Exfiltration
Ollama's desktop app is vulnerable to phishing overlay and data exfiltration attacks via indirect prompt injection, overwriting the app with an attacker's site.
Read more
Report
ChatGPT for Google Sheets Exfiltrates Workbooks
ChatGPT for Google Sheets is vulnerable to data exfiltration and phishing overlay attacks that affect workbooks across the victim's account after an indirect prompt injection in a single sheet.
Read more
Report
Codex Exfiltrates Connector Data
Codex for Everything was susceptible to data exfiltration via indirect prompt injection, exposing sensitive data from connected apps with no human-in-the-loop steps required.
Read more
Report
Microsoft Copilot Cowork Exfiltrates Files
Microsoft Copilot Cowork is vulnerable to file exfiltration attacks via indirect prompt injection as a result of insecure automatic action approvals for sending Emails and Teams messages.
Read more
Report
Show more news
Tech stack
Technologies named in job postings at PromptArmor over the last 12 months, by layer, with the share of postings for each.
Technologies in use
1
Postings analysed
1
Stack modernity
90/100AI adopter
AI & ML
LLM
Sign in to see how your skills match this stack
Sign In
Growth
Hiring Momentum
48/100
Stable
Open positions
1
0 opened / 0 closed in 30 days
ATS activity
Every ~4 hours
Today
Hiring Dynamics
+100%
Hiring Focus
The percentage next to each role is its share of the company's job openings over the last 90 days; the arrow shows the shift versus the previous period.
Sales
100% ▲
Offices
Where the company hires and what each office is for
Cities
1
Hiring now
1
Countries
1
Busiest office
San Francisco
San Francisco
United States
HQ
1 open roles 1 posted in 90 days 10-50 est. staff $120k Avg Salary
hires for Sales