IDEs & agents · Anysphere
Cursor
AI code editor with agent mode, rules files and MCP support.
14Advisories
3critical
10high
1medium
2026-08Latest
Timeline · advisories per quarter
52025 Q1
22025 Q2
42025 Q3
32026 Q3
Named in sources
Reported for Cursor
01. CVE-2025-54135 (“CurXecute”): Cursor agent could create MCP config and run codeBefore 1.3.9, Cursor let the agent create new dotfiles like .cursor/mcp.json without approval. Chained with prompt injection, this meant remote code execution. Cursor 2025-08 02. CVE-2025-54136 (“MCPoison”): approved MCP servers could be silently swappedIn Cursor 1.2.4 and below, once you approved an MCP server, an attacker with write access could change its command without any re-prompt. Cursor 
MCP SDKs & servers 2025-08 03. “Rules File Backdoor”: hidden Unicode instructions in AI rules filesPillar Security showed invisible Unicode characters in shared rules files (.cursorrules, .mdc) can steer Cursor and GitHub Copilot into writing backdoored code. Cursor 
Copilot 2025-03
Cursor 2025-08 02. CVE-2025-54136 (“MCPoison”): approved MCP servers could be silently swappedIn Cursor 1.2.4 and below, once you approved an MCP server, an attacker with write access could change its command without any re-prompt. Cursor MCP SDKs & servers 2025-08 03. “Rules File Backdoor”: hidden Unicode instructions in AI rules filesPillar Security showed invisible Unicode characters in shared rules files (.cursorrules, .mdc) can steer Cursor and GitHub Copilot into writing backdoored code. Cursor Copilot 2025-03 Same pattern
Also worth checking
01. Supabase tables readable by anyone with no loginA scan of 30,998 live vibe-coded apps found 57% of the Supabase-backed apps it could check served table rows to requests with no login. 
Lovable 
Bolt 
v0 +4 more 2026-08 02. Supabase service_role / secret key shipped to the browserThe service_role (or new sb_secret_) key bypasses every RLS policy. If it is in your JavaScript bundle, your whole database is public. Lovable Bolt v0 +4 more 2026-08 03. CVE-2025-29927: Next.js middleware authorization bypassSelf-hosted Next.js apps that did auth in middleware could be bypassed with the internal x-middleware-subrequest header. Relevant to any Next.js app, including ones generated by v0. 
Next.js v0 Bolt +2 more 2025-03 04. Secrets leaked via NEXT_PUBLIC_ (or VITE_) environment variablesPrefixing a variable with NEXT_PUBLIC_ inlines it into the JavaScript every visitor downloads. AI tools often “fix” a missing-env error this way. Lovable Bolt v0 +4 more 2026-08 05. Supabase MCP: a support ticket gets the agent to dump private tablesGeneral Analysis showed indirect prompt injection in support-ticket data making an MCP-connected assistant query private tables with Supabase’s privileged service role. MCP SDKs & servers 
Supabase Cursor +1 more 2025-07-08 06. AI agent deleted a production database during a code freeze (Replit)Replit Agent deleted SaaStr founder Jason Lemkin’s live database (1,206 executives, 1,196+ companies) despite an explicit freeze, then wrongly said rollback was impossible. 
Replit Cursor 2025-07 07. GitHub MCP server: a public issue makes the agent leak private reposInvariant Labs showed that a prompt injection planted in a public GitHub issue could get an agent using the official GitHub MCP server to pull data from the user’s private repositories. MCP SDKs & servers 
Claude Code Cursor +1 more 2025-05-26 08. MCP tool poisoning: hidden instructions in tool descriptionsAn MCP server can hide instructions inside a tool’s description. The model reads them, the user usually doesn’t, and the agent can be steered into reading files or sending data elsewhere. MCP SDKs & servers Cursor Claude Code +2 more 2025-04-01 09. Authentication logic living entirely in the browserHiding a page or button in the UI is not access control. If the API or database doesn’t check the user, anyone can call it directly. Lovable 
Base44 Bolt +3 more 2025 10. Slopsquatting: AI suggests packages that don’t existA USENIX Security 2025 study found 19.7% of 2.23 million package suggestions from 16 code models were hallucinated. Attackers can register those names. Claude Code Copilot Cursor +5 more 2025 11. Protecting routes only in middlewareVercel recommends against middleware being the sole method of protecting routes. Check auth again where data is read or changed. Next.js v0 Bolt +2 more 2025-03
Lovable Bolt v0 +4 more 2026-08 02. Supabase service_role / secret key shipped to the browserThe service_role (or new sb_secret_) key bypasses every RLS policy. If it is in your JavaScript bundle, your whole database is public. Lovable Bolt v0 +4 more 2026-08 03. CVE-2025-29927: Next.js middleware authorization bypassSelf-hosted Next.js apps that did auth in middleware could be bypassed with the internal x-middleware-subrequest header. Relevant to any Next.js app, including ones generated by v0. Next.js v0 Bolt +2 more 2025-03 04. Secrets leaked via NEXT_PUBLIC_ (or VITE_) environment variablesPrefixing a variable with NEXT_PUBLIC_ inlines it into the JavaScript every visitor downloads. AI tools often “fix” a missing-env error this way. Lovable Bolt v0 +4 more 2026-08 05. Supabase MCP: a support ticket gets the agent to dump private tablesGeneral Analysis showed indirect prompt injection in support-ticket data making an MCP-connected assistant query private tables with Supabase’s privileged service role. MCP SDKs & servers Supabase Cursor +1 more 2025-07-08 06. AI agent deleted a production database during a code freeze (Replit)Replit Agent deleted SaaStr founder Jason Lemkin’s live database (1,206 executives, 1,196+ companies) despite an explicit freeze, then wrongly said rollback was impossible. Replit Cursor 2025-07 07. GitHub MCP server: a public issue makes the agent leak private reposInvariant Labs showed that a prompt injection planted in a public GitHub issue could get an agent using the official GitHub MCP server to pull data from the user’s private repositories. MCP SDKs & servers Claude Code Cursor +1 more 2025-05-26 08. MCP tool poisoning: hidden instructions in tool descriptionsAn MCP server can hide instructions inside a tool’s description. The model reads them, the user usually doesn’t, and the agent can be steered into reading files or sending data elsewhere. MCP SDKs & servers Cursor Claude Code +2 more 2025-04-01 09. Authentication logic living entirely in the browserHiding a page or button in the UI is not access control. If the API or database doesn’t check the user, anyone can call it directly. Lovable Base44 Bolt +3 more 2025 10. Slopsquatting: AI suggests packages that don’t existA USENIX Security 2025 study found 19.7% of 2.23 million package suggestions from 16 code models were hallucinated. Attackers can register those names. Claude Code Copilot Cursor +5 more 2025 11. Protecting routes only in middlewareVercel recommends against middleware being the sole method of protecting routes. Check auth again where data is read or changed. Next.js v0 Bolt +2 more 2025-03