CVE-2026-65056Disclosure

LOWCVSS 8.3 · HIGH

Signal is active with 2 mentions in latest observed window

Immediate actions

Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

mcp-webresearch 0.1.7 contains a server-side request forgery vulnerability that allows attackers to access internal network services by supplying loopback, link-local, or cloud metadata addresses to the visit_page tool, which only validates the URL protocol without filtering private or reserved IP ranges. Attackers can steer the LLM-controlled URL argument through prompt injection to navigate the server's Playwright browser to internal endpoints such as cloud instance metadata services, causing the server to return sensitive internal page content including credentials into the model context.

Back to dashboard

0.0/ 10 priority

Sources & remediation

Other references

Weakness type (CWE)

CWE-918

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

NONE

Momentum

NONE

Threat summary

2 mentions across 1 observed day

What's happening

Technical details provided in 2 signals
Disclosure: 2 classified signals
2 total mentions across 1 day

Deep dive

Activity timeline2 mentions / 1d

Signal classification1 categories

Disclosure

2100.0%

Referenced assets1 URL

By indicator

https://nvd.nist.gov/vuln/detail/CVE-2026-65056

Full discourse2 posts

Mohi@disismohi91d
Disclosure
Your AI agent just became an SSRF vector. CVE-2026-65056 in mcp-webresearch 0.1.7: prompt injection can steer the tool to fetch cloud metadata endpoints and return credentials into model context. CVSS 8.3 HIGH. Here's what to check Wednesday:
Post summary
A CVE‑2026-65056 vulnerability in mcp-webresearch 0.1.7 allows prompt injection to perform SSRF against cloud metadata endpoints, enabling credential leakage; the issue has a CVSS 8.3 high rating.
101101.1K
73 followersView on X
Mohi@disismohi91d
Disclosure
LLM-controlled SSRF is a new class of vulnerability. The CVE is public, the package is on npm, and most teams haven't threat-modeled this yet. https://nvd.nist.gov/vuln/detail/CVE-2026-65056
Post summary
The tweet announces the CVE‑2026‑65056 as a newly discovered LLM‑controlled SSRF flaw in an npm package, noting its public status and lack of prior threat modeling but providing no evidence of exploitation or patches.
0000044
73 followersView on X

Explore more

Back to dashboard