CVE-2025-67743VulnerabilityPublished 23 Dec 2025

CVE-2025-67743: LearningCircuit local-deep-research · Server-Side Request Forgery (SSRF)

Affects LearningCircuit local-deep-researchSource CVE Database V5

Not known to be exploited · CVSS 6.3 Medium : upgrade to 1.3.9 when convenient.

Data as of 25 Oct 2026, 19:02 UTC

CVSS 3.1 base score

6.3Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.3% chance of exploitation in 30 days – higher than 24% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 1.3.9

CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N

Attack Vector: Network
Attack Complexity: High
Privileges Required: Low
User Interaction: None
Scope: Changed
Confidentiality: High
Integrity: None
Availability: None

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: High: A successful attack depends on conditions beyond the attacker's control. That is, a successful attack cannot be accomplished at will, but requires the attacker to invest in some measurable amount of effort in preparation or execution against the vulnerable component before a successful attack can be expected. For example, a successful attack may require an attacker to: gather knowledge about the environment in which the vulnerable target/component exists; prepare the target environment to improve exploit reliability; or inject themselves into the logical network path between the target and the resource requested by the victim in order to read and/or modify network communications (e.g., a man in the middle attack).
Privileges Required: Low: The attacker is authorized with (i.e., requires) privileges that provide basic user capabilities that could normally affect only settings and files owned by a user. Alternatively, an attacker with Low privileges may have the ability to cause an impact only to non-sensitive resources.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Changed: An exploited vulnerability can affect resources beyond the security scope managed by the security authority of the vulnerable component. In this case, the vulnerable component and the impacted component are different and managed by different security authorities.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: None: There is no impact to availability within the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 23 Dec 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 2026-10-25.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade learningcircuit/local-deep-research to 1.3.9.

Affected software

Product	Affected	Fixed in
GitHublearningcircuit/local-deep-research`pkg:github/learningcircuit/local-deep-research`Other threats	Affected <1.3.9 >=1.3.0	Fixed in 1.3.9

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

European organizations should immediately upgrade local-deep-research to version 1.3.9 or later, where the SSRF vulnerability has been patched. If immediate upgrading is not feasible, implement strict network egress filtering to block outbound HTTP requests from the application server to internal IP ranges and cloud metadata IP addresses (e.g., 169.254.169.254 for AWS). Employ application-layer firewall rules or API gateways to validate and sanitize URLs submitted to the download service, ensuring only trusted domains are reachable. Conduct thorough code reviews and penetration testing focusing on SSRF vectors within the application. Monitor logs for unusual outbound requests or access patterns indicative of SSRF exploitation attempts. Additionally, restrict API access to trusted users and enforce strong authentication and authorization controls to limit the attack surface. For cloud environments, implement metadata service protections such as AWS IMDSv2 or equivalent to reduce risk from SSRF attacks. Finally, maintain an incident response plan tailored to SSRF exploitation scenarios.

Description

Local Deep Research is an AI-powered research assistant for deep, iterative research. In versions from 1.3.0 to before 1.3.9, the download service (download_service.py) makes HTTP requests using raw requests.get() without utilizing the application's SSRF protection (safe_requests.py). This can allow attackers to access internal services and attempt to reach cloud provider metadata endpoints (AWS/GCP/Azure), as well as perform internal network reconnaissance, by submitting malicious URLs through the API, depending on the deployment and surrounding controls. This issue has been patched in version 1.3.9.

Impact

For European organizations, this SSRF vulnerability poses a significant risk to confidentiality, particularly for those deploying local-deep-research in environments with access to sensitive internal services or cloud infrastructure. Exploitation could lead to unauthorized disclosure of cloud metadata, which often contains temporary credentials or tokens that can be leveraged for lateral movement or privilege escalation within cloud environments. This is especially critical for organizations relying on AWS, GCP, or Azure, as exposure of metadata endpoints can compromise entire cloud workloads. Internal network reconnaissance enabled by SSRF can also facilitate further attacks against internal services, increasing the attack surface. Given the AI assistant's role in research, organizations in sectors such as academia, finance, healthcare, and government may be targeted due to the sensitivity of their data and research outputs. The medium CVSS score reflects moderate ease of exploitation combined with significant confidentiality impact. The absence of known exploits reduces immediate risk but does not eliminate it, especially as attackers may develop exploits post-disclosure. Failure to patch or mitigate this vulnerability could lead to data breaches, regulatory non-compliance under GDPR, and reputational damage.

Summary

CVE-2025-67743 is a Server-Side Request Forgery (SSRF) vulnerability identified in the LearningCircuit product local-deep-research, specifically affecting versions from 1.3.0 up to but not including 1.3.9. The vulnerability stems from the download_service.py component making HTTP requests using raw requests.get() calls without leveraging the application's built-in SSRF protections implemented in safe_requests.py. This design flaw allows an attacker who can interact with the API to submit crafted URLs that the server will fetch, potentially accessing internal network resources that are otherwise inaccessible externally. Critical targets include cloud provider metadata endpoints such as those from AWS, Google Cloud Platform, and Microsoft Azure, which can expose sensitive credentials or configuration data. The vulnerability requires the attacker to have at least low-level privileges to interact with the API but does not require user interaction beyond that. The attack complexity is high due to the need to craft specific requests and potentially bypass surrounding network controls. The vulnerability impacts confidentiality by exposing sensitive internal resources but does not affect integrity or availability directly. The issue was publicly disclosed on December 23, 2025, with a CVSS v3.1 base score of 6.3, categorized as medium severity. No known exploits have been reported in the wild, but the risk remains significant due to the potential exposure of cloud metadata services. The vendor addressed the vulnerability in version 1.3.9 by ensuring all HTTP requests utilize the safe_requests.py protections to prevent SSRF attacks.

CWE-918Server-Side Request Forgery (SSRF) (opens in a new tab)
Base weaknessCWE Top 25 (2025): #22OWASP Top 10 A01:2025: Broken Access Control (opens in a new tab)
The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.
OWASP Cheat Sheets
Server Side Request Forgery Prevention (opens in a new tab)
Unvalidated Redirects and Forwards (opens in a new tab)
Cross Site Scripting Prevention (opens in a new tab)
DOM based XSS Prevention (opens in a new tab)
Authorization (opens in a new tab)
OWASP ASVS 4.0.3
V12.6.1 (opens in a new tab)
V5.2.6 (opens in a new tab)
Attack patterns
Server Side Request Forgery (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 23 Dec 2025, 04:07 UTC

WeaknessesCWE-918

Technical details

References

Community reviews

Related threats