Fix memory bug in grammar parser (#7194)

The llama.cpp grammar parser had a bug where forgetting to add a closing
quotation mark to strings would cause parsing to crash. Anyone running a
server on a public endpoint is advised to upgrade. To reproduce this bug

    ./llamafile -m foo.gguf -p bar --grammar 'root::="'

Credit for discovering and reporting this issue goes to Eclypsium
Security Researcher Richard Johnson <Richard.johnson@eclypsium.com>.
This commit is contained in:
Justine Tunney 2024-05-10 07:01:08 -04:00 committed by GitHub
parent f89fe2732c
commit 4e3880978f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 21 additions and 5 deletions

View file

@ -142,6 +142,9 @@ namespace grammar_parser {
pos++;
last_sym_start = out_elements.size();
while (*pos != '"') {
if (!*pos) {
throw std::runtime_error("unexpected end of input");
}
auto char_pair = parse_char(pos);
pos = char_pair.second;
out_elements.push_back({LLAMA_GRETYPE_CHAR, char_pair.first});
@ -156,6 +159,9 @@ namespace grammar_parser {
}
last_sym_start = out_elements.size();
while (*pos != ']') {
if (!*pos) {
throw std::runtime_error("unexpected end of input");
}
auto char_pair = parse_char(pos);
pos = char_pair.second;
enum llama_gretype type = last_sym_start < out_elements.size()
@ -164,6 +170,9 @@ namespace grammar_parser {
out_elements.push_back({type, char_pair.first});
if (pos[0] == '-' && pos[1] != ']') {
if (!pos[1]) {
throw std::runtime_error("unexpected end of input");
}
auto endchar_pair = parse_char(pos + 1);
pos = endchar_pair.second;
out_elements.push_back({LLAMA_GRETYPE_CHAR_RNG_UPPER, endchar_pair.first});