security: harden safetensors/JSON parsers against malicious model files
A downloaded (supply-chain) model file was fully trusted by the loader. Three memory-safety holes, all reachable by pointing the engine at a crafted shard — demonstrated crashing on pre-fix, now rejected fail-closed: st.h (safetensors): - header length `hlen` (u64 from the file) was unbounded before malloc(hlen+1): a crafted value overflows (malloc(0) then hdr[hlen]=0 OOB) or forces a giant allocation. Now bounded to the file size and a 512 MB cap; malloc NULL-checked. - json_get() returns NULL for missing/mistyped fields, but dtype/data_offsets/ shape were dereferenced blind (off->kids[0]) — a header omitting data_offsets SIGSEGV'd (verified). Now type/arity-checked before use. - data_offsets [a0,b0] were trusted: b0<a0 gave a negative nbytes -> malloc((size_t)) giant and an oversized memcpy into the caller's buffer in st_read_f32 (heap overflow); off could point outside the file. Now validated 0<=a0<=b0 and data_start+b0<=filesize. json.h: j_parse_val recursed with no depth limit -> stack overflow on nested input like [[[[...]]]]. Added J_MAX_DEPTH=1024 (headers are ~3 deep); wide-but- flat objects like the GLM header are unaffected (depth is decremented per return). eval_glm.py: tempfile.mktemp() -> mkstemp() — closes the TOCTOU/symlink race on a shared tmp dir (CWE-377). Network path (openai_server.py + serve SUBMIT parser) audited separately and is already sound: hmac.compare_digest auth, MAX_BODY cap, resolve()+relative_to traversal guard, list-form subprocess, bounded/validated SUBMIT header. All 62 tests pass; valid GLM/OLMoE shards load unchanged. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
@@ -26,8 +26,14 @@ typedef struct {
|
||||
const char *s;
|
||||
char *arena; /* buffer per le stringhe smontate */
|
||||
size_t acap, aoff;
|
||||
int depth; /* annidamento corrente: bound contro lo stack-overflow
|
||||
* da JSON malevolo tipo [[[[...]]]] (discesa ricorsiva) */
|
||||
} jparser;
|
||||
|
||||
/* tetto di annidamento: gli header safetensors / config sono piatti (profondita'
|
||||
* ~3). 1024 e' larghissimo per input legittimi e ben sotto il limite di stack. */
|
||||
#define J_MAX_DEPTH 1024
|
||||
|
||||
static char *j_dup(jparser *p, const char *b, int n) {
|
||||
/* ogni stringa ha la sua allocazione: un'arena con realloc sposterebbe il
|
||||
* buffer invalidando i puntatori gia' emessi (use-after-free). */
|
||||
@@ -91,10 +97,11 @@ static jval *j_parse_val(jparser *p) {
|
||||
char c = *p->s;
|
||||
if (c == '"') { jval *v = j_new(J_STR); v->str = j_parse_str_raw(p); return v; }
|
||||
if (c == '{') {
|
||||
if (++p->depth > J_MAX_DEPTH) { p->depth--; return j_new(J_NULL); }
|
||||
p->s++; jval *v = j_new(J_OBJ);
|
||||
int cap = 8; v->keys = malloc(cap * sizeof(char*)); v->kids = malloc(cap * sizeof(jval*));
|
||||
j_ws(p);
|
||||
if (*p->s == '}') { p->s++; return v; }
|
||||
if (*p->s == '}') { p->s++; p->depth--; return v; }
|
||||
for (;;) {
|
||||
j_ws(p);
|
||||
char *key = j_parse_str_raw(p);
|
||||
@@ -107,13 +114,15 @@ static jval *j_parse_val(jparser *p) {
|
||||
if (*p->s == '}') { p->s++; break; }
|
||||
break;
|
||||
}
|
||||
p->depth--;
|
||||
return v;
|
||||
}
|
||||
if (c == '[') {
|
||||
if (++p->depth > J_MAX_DEPTH) { p->depth--; return j_new(J_NULL); }
|
||||
p->s++; jval *v = j_new(J_ARR);
|
||||
int cap = 8; v->kids = malloc(cap * sizeof(jval*));
|
||||
j_ws(p);
|
||||
if (*p->s == ']') { p->s++; return v; }
|
||||
if (*p->s == ']') { p->s++; p->depth--; return v; }
|
||||
for (;;) {
|
||||
jval *val = j_parse_val(p);
|
||||
if (v->len == cap) { cap *= 2; v->kids = realloc(v->kids, cap*sizeof(jval*)); }
|
||||
@@ -123,6 +132,7 @@ static jval *j_parse_val(jparser *p) {
|
||||
if (*p->s == ']') { p->s++; break; }
|
||||
break;
|
||||
}
|
||||
p->depth--;
|
||||
return v;
|
||||
}
|
||||
if (c == 't') { p->s += 4; jval *v = j_new(J_BOOL); v->boolean = 1; return v; }
|
||||
@@ -134,7 +144,7 @@ static jval *j_parse_val(jparser *p) {
|
||||
|
||||
/* API */
|
||||
static jval *json_parse(const char *text, char **arena_out) {
|
||||
jparser p = { text, NULL, 0, 0 };
|
||||
jparser p = { text, NULL, 0, 0, 0 };
|
||||
jval *v = j_parse_val(&p);
|
||||
if (arena_out) *arena_out = p.arena; else free(p.arena);
|
||||
return v;
|
||||
|
||||
Reference in New Issue
Block a user