16
CVEs
2
Critical
5
High
0
KEV
7
PoC
1
Unpatched C/H
87.5%
Patch Rate
0.4%
Avg EPSS
Severity Breakdown
CRITICAL
2
HIGH
5
MEDIUM
3
LOW
6
Monthly CVE Trend
Affected Products (9)
Top Risky CVEs
| CVE | Summary | Severity | CVSS | EPSS | Priority | Signals |
|---|---|---|---|---|---|---|
| CVE-2026-61736 | Cross-origin data theft in LightRAG server versions prior to 1.5.4 allows any malicious website to make authenticated, credentialed API calls on behalf of a logged-in victim because the server ships with CORS_ORIGINS=* paired with allow_credentials=True. When an authenticated LightRAG user browses to an attacker-controlled page, that page can silently read documents and knowledge-graph data or issue destructive requests such as deleting the entire document store. No public exploit has been identified at time of analysis and the flaw is not in CISA KEV, but the fix is confirmed released in version 1.5.4. | CRITICAL | 9.3 | 0.3% | 67 |
PoC
|
| CVE-2026-61740 | Authentication bypass in HKUDS LightRAG before 1.5.4 lets a remote unauthenticated attacker defeat X-API-Key protection when the server runs in the API-key-only profile (LIGHTRAG_API_KEY set, AUTH_ACCOUNTS unset). Because auth.py falls back to a public hardcoded DEFAULT_TOKEN_SECRET and /auth-status and /login freely mint guest JWTs, combined_dependency honored a guest token before ever checking the API key, exposing document read/upload/delete, graph mutation, and query endpoints. No public exploit is identified at time of analysis, but the underlying fix (PR #3319) ships a regression test showing that forging a valid guest token with the default secret is trivial; fixed in 1.5.4. | CRITICAL | 9.3 | 0.4% | 46 |
PoC
|
| CVE-2026-48716 | Arbitrary file write in HKUDS Nanobot's WhatsApp bridge (versions 0.1.5.post3 and prior) allows remote unauthenticated attackers to write attacker-controlled content to arbitrary filesystem locations by sending a WhatsApp document message with a path-traversal sequence in its fileName field. Because both the destination path and the file content are attacker-controlled, exploitation yields a write-anywhere primitive that can be escalated to remote code execution (e.g., by overwriting authorized_keys or shell startup files). No public exploit identified at time of analysis; a fix is planned for version 0.1.5.post4. | HIGH | 8.7 | 0.3% | 44 |
No patch
|
| CVE-2026-58168 | Privilege escalation via missing authorization in HKUDS DeepTutor before 1.4.10 lets any authenticated low-privilege user invoke deployment-wide MCP (Model Context Protocol) tools they were never granted. The root cause is the allowed_mcp_tools function in deeptutor/multi_user/tool_access.py returning None (interpreted as 'allow all') instead of a denied result when the mcp_tools key is omitted from a user's grant, so a regular user - or prompt-injected content running inside their session - can enumerate and call filesystem, shell, and browser MCP servers. No public exploit is identified at the time of analysis and it is not in CISA KEV, but a vendor patch (v1.4.10) is available and the issue was reported by VulnCheck. | HIGH | 7.7 | 0.4% | 39 |
|
| CVE-2026-58169 | Remote code execution in HKUDS Vibe-Trading before 0.1.10 is reachable via a DNS-rebinding attack against its local API server, which trusts the TCP peer address to waive the API_AUTH_KEY bearer-token check for loopback clients, performs no Host-header validation, and binds to 0.0.0.0 with credentialed CORS by default. Because loopback requests also auto-enable shell tools, a malicious web page visited by the victim can issue authenticated POST /swarm/runs calls with a built-in preset that permits the bash tool, executing arbitrary commands as the API process user and also overwriting LLM and data-source settings to redirect provider traffic and exfiltrate credentials. No CISA KEV listing or EPSS score was provided and no public exploit identified at time of analysis, though the issue was reported by VulnCheck. | HIGH | 7.7 | 0.3% | 39 |
|
| CVE-2026-58170 | Trading mandate forgery in HKUDS Vibe-Trading before 0.1.10 lets an admitted (low-privileged) caller supply a proposal identifier containing path traversal sequences so the application loads an attacker-controlled JSON file as an authoritative live trading mandate. Because ceiling/limit validation is skipped when ceilings are absent, the attacker fully controls the committed mandate, enabling unauthorized live trades. A vendor patch exists and the issue was reported by VulnCheck, but there is no public exploit identified at time of analysis and it is not listed in CISA KEV. | HIGH | 7.2 | 0.4% | 36 |
|
| CVE-2026-56695 | Cross-session information disclosure in HKUDS OpenHarness ohmo gateway allows admitted remote senders to invoke /resume and /summary slash commands, which were incorrectly registered with remote_invocable=True by default, to enumerate and load arbitrary saved session snapshots by ID. Successful exploitation exposes another user's private prompts, credentials, tool outputs, and file paths exchanged through shared gateway channels (e.g. Slack threads). No public exploit identified at time of analysis, but a vendor patch and detailed test cases (PR #276) make the issue easy to weaponize. | HIGH | 7.1 | 0.2% | 36 |
|
| CVE-2026-85030 | Business logic manipulation in HKUDS AI-Trader's unauthenticated selfRegister API endpoint allows remote attackers to supply an arbitrary initial_balance value, inflating their simulated starting cash in the trading competition platform. Critically, the description confirms that profit_percent_for_display() and challenge scoring's return_pct both normalize against the inflated starting capital, making percentage-based returns immune; exploitation achieves only cosmetic inflation of absolute cash and equity leaderboard columns, not artificial percent-return gains. A public proof-of-concept exploit exists per a GitHub security advisory and VulDB entry 398295, though no active exploitation (KEV) has been identified. | LOW | 2.9 | 0.4% | 35 |
PoC
No patch
|
| CVE-2026-90809 | Argument injection in HKUDS nanobot's ExecTool shell execution guard allows remote unauthenticated attackers to bypass the command allowlist/denylist filter by embedding newline or carriage-return characters in a command string, causing injected shell segments to execute without inspection. Affected versions are nanobot 0.2.0 and 0.2.1; the root cause is that `_split_shell_segments()` recognized `;` and `|` as command-chain delimiters but not `\n` or `\r`, so a payload on its own line was never checked against allow/deny patterns. No public exploit or CISA KEV listing is identified; patch commit af582246 is available. | MEDIUM | 6.9 | 0.3% | 34 |
|
| CVE-2026-19243 | OS command injection in HKUDS nanobot 0.2.0 and 0.2.1 allows a low-privileged remote attacker to bypass the configured shell command allowlist by submitting chained shell commands using operators such as `&&`, `||`, `;`, `|`, or `&`. The `ExecTool._guard_command` method in `shell.py` validated the entire raw command string as a single unit against allow patterns, meaning only the first chained segment needed to match - subsequent malicious segments executed unchecked. A public proof-of-concept exploit exists; the vulnerability is not listed in CISA KEV but the CVSS 4.0 E:P modifier confirms publicly available exploit code elevates urgency beyond the base score of 5.3. | LOW | 2.1 | 1.6% | 32 |
PoC
|
| CVE-2026-19246 | Server-side request forgery in HKUDS nanobot up to 0.2.1 allows authenticated remote attackers to make the server issue HTTP requests to arbitrary internal endpoints by manipulating URLs returned by AI image generation providers. The `_download_image_data_url` function in `nanobot/providers/image_generation.py` fetched provider-returned image URLs directly via `client.get(url)` without routing through the existing `validate_url_target` SSRF guard in `security/network.py`, leaving cloud metadata endpoints (e.g., 169.254.169.254), RFC1918 ranges, and internal services reachable. A public POC exploit exists; a patch is available on the main branch as PR #5095 and is planned for release in v0.3.1. No CISA KEV listing; exploitation is not confirmed at mass scale. | LOW | 2.1 | 0.2% | 31 |
PoC
|
| CVE-2026-58173 | Path traversal in Vibe-Trading before version 0.1.10 allows low-privileged authenticated network attackers to write arbitrary Markdown files outside the application's intended memory root directory. The `remember` tool fails to sanitize the `memory_type` parameter before constructing filesystem paths, enabling traversal sequences to escape the memory root and land files at attacker-controlled locations on the server. No public exploit or CISA KEV listing has been identified, but the high integrity impact and low attack complexity make patching urgent for any internet-exposed deployment. | MEDIUM | 6.0 | 0.3% | 30 |
|
| CVE-2026-19244 | MCP resource and prompt wrappers in HKUDS nanobot 0.2.0 and 0.2.1 bypass operator-defined `enabledTools` access restrictions, allowing MCP servers to register capabilities beyond the intended scope. Operators who configure a specific tool allowlist to restrict what an MCP server can contribute to a nanobot agent find that resources and prompts from that server are registered unconditionally, exposing capabilities that were explicitly intended to be blocked. A public proof-of-concept exploit exists; this CVE is not in the CISA KEV catalog, so confirmed widespread active exploitation is not established. | LOW | 2.0 | 0.3% | 30 |
PoC
|
| CVE-2026-19245 | Login-shell environment variable leakage in HKUDS nanobot up to 0.2.1 exposes sensitive environment variables to local low-privilege users during agent-driven shell command execution. The `ExecTool._prepare_command` function in `shell.py` defaulted to invoking bash/zsh with the `-l` (login shell) flag, causing system and user profile startup scripts to be sourced and potentially re-exporting credentials, API keys, or tokens into the execution environment where they could be read by the invoking user. A publicly available proof-of-concept exploit exists; no active exploitation has been confirmed (not listed in CISA KEV). The vendor-released fix in v0.3.0 changes the default from login-shell to non-login-shell execution. | LOW | 1.9 | 0.1% | 30 |
PoC
|
| CVE-2026-56696 | Remote prompt injection in OpenHarness allows low-privileged messaging channel participants to persistently corrupt AI agent system prompts by exploiting unguarded /issue and /pr_comments slash commands. Any authenticated member of a connected remote channel (e.g., Slack via the ohmo gateway) can write arbitrary attacker-controlled Markdown into .openharness/issue.md and .openharness/pr_comments.md, which are subsequently injected into the agent's runtime system prompt on every subsequent invocation. No public exploit or CISA KEV listing exists at time of analysis, but the upstream patch (PR #272, commit 27bb93b) confirms the vulnerability and its mechanism. | MEDIUM | 5.3 | 0.2% | 26 |
|