mirror of
https://github.com/hanzoai/insights.git
synced 2026-11-02 14:32:45 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
53 lines
2.1 KiB
YAML
53 lines
2.1 KiB
YAML
rules:
|
|
- id: sql-injection-user-input
|
|
mode: taint
|
|
pattern-sources:
|
|
- patterns:
|
|
- pattern-either:
|
|
# Django request parameters
|
|
- pattern: $REQ.GET.get(...)
|
|
- pattern: $REQ.POST.get(...)
|
|
- pattern: $REQ.GET[...]
|
|
- pattern: $REQ.POST[...]
|
|
- pattern: $REQ.data.get(...)
|
|
- pattern: $REQ.data[...]
|
|
- pattern: $REQ.query_params.get(...)
|
|
- pattern: $REQ.query_params[...]
|
|
# DRF serializer data
|
|
- pattern: $SERIALIZER.validated_data.get(...)
|
|
- pattern: $SERIALIZER.validated_data[...]
|
|
pattern-sinks:
|
|
# String format in execute (works well with taint tracking)
|
|
- pattern: $C.execute("...".format(...))
|
|
- pattern: $C.execute("..." % ...)
|
|
- pattern: $C.execute($A + ...)
|
|
- pattern: $M.raw("...".format(...))
|
|
- pattern: $M.raw("..." % ...)
|
|
pattern-sanitizers:
|
|
# Type conversions that neutralize injection
|
|
- pattern: int(...)
|
|
- pattern: float(...)
|
|
- pattern: str(int(...))
|
|
- pattern: str(float(...))
|
|
# Explicit escaping functions
|
|
- pattern: escape_datastore_identifier(...)
|
|
- pattern: escape_datastore_string(...)
|
|
# psycopg2 safe SQL composition
|
|
- pattern: sql.Identifier(...)
|
|
- pattern: sql.Literal(...)
|
|
- pattern: sql.SQL(...).format(...)
|
|
message: |
|
|
SQL injection risk: User input flows to SQL query without parameterization.
|
|
Use parameterized queries: cursor.execute("SELECT * FROM t WHERE id = %s", [id])
|
|
For identifiers, use escape_datastore_identifier() or psycopg2 sql.Identifier().
|
|
languages: [python]
|
|
severity: ERROR
|
|
paths:
|
|
exclude:
|
|
- '**/.semgrep/**'
|
|
- '**/test/**'
|
|
- '**/tests/**'
|
|
- '**/*_test.py'
|
|
- '**/test_*.py'
|
|
- '**/conftest.py'
|