Uncontrolled Recursion in llama.cpp

Executive Summary

llama.cpp versions up to b5693 have a flaw in common/json-schema-to-grammar.cpp where deeply nested JSON schemas cause uncontrolled recursion. This crashes the server by exhausting the recursion stack, leading to a denial of service.

Useful 0 Not Useful 0

Detection Guidance

To detect this vulnerability, monitor for crashes in llama.cpp processes handling POST /completions requests. Check server logs for stack overflow errors or segmentation faults during JSON schema processing. Use tools like strace or gdb to trace recursive calls in SchemaConverter::visit and _generate_union_rule functions. Test with a deeply nested JSON schema (depth 7000+) to trigger the issue.

Useful 0 Not Useful 0

Impact Analysis

An attacker could send a specially crafted JSON schema to the POST /completions endpoint, causing the server to crash. This disrupts service availability for all users relying on that endpoint.

Useful 0 Not Useful 0

Compliance Impact

This vulnerability could indirectly impact compliance with GDPR or HIPAA by enabling denial-of-service attacks that disrupt service availability. Uncontrolled recursion may lead to system crashes, potentially causing downtime for applications handling sensitive data. However, the vulnerability itself does not directly violate these standards unless it results in unauthorized data access or prolonged service unavailability affecting data subjects.

Useful 0 Not Useful 0

Mitigation Strategies

Immediately disable the POST /completions endpoint if not required. Implement input validation to reject excessively nested JSON schemas. Apply network-level rate limiting to prevent abuse. Monitor for unusual traffic patterns targeting the vulnerable endpoint. Consider upgrading to a patched version if available.

Useful 0 Not Useful 0