Server-side request forgery via unrestricted APIChain URLs
Published Oct 20, 2023 · Updated Sep 12, 2024
Server-side request forgery in LangChain APIChain before 0.0.329 allows remote attackers to retrieve data from arbitrary URLs via prompt injection. APIChain accepts an LLM-generated URL and passes it directly to requests_wrapper.get or aget without restricting its scheme and domain. An application must expose attacker-controlled prompts to APIChain; successful abuse reads resources reachable by the server and can feed their content into downstream tasks.
Summary
What happened
Server-side request forgery in LangChain APIChain before 0.0.329 allows remote attackers to retrieve data from arbitrary URLs via prompt injection. APIChain accepts an LLM-generated URL and passes it directly to requests_wrapper.get or aget without restricting its scheme and domain. An application must expose attacker-controlled prompts to APIChain; successful abuse reads resources reachable by the server and can feed their content into downstream tasks.
The record
- CVE
- CVE-2023-32786
- Published
- Oct 20, 2023
- Updated
- Sep 12, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-74, CWE-918, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Oct 20, 2023CVE publishedPublication date reported by the CVE source.
- Sep 12, 2024Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- LangChain APIChain arbitrary URL access notebookproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo