Initial commit: hardened DeerFlow factory
Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection hardening: - New deerflow.security package: content_delimiter, html_cleaner, sanitizer (8 layers — invisible chars, control chars, symbols, NFC, PUA, tag chars, horizontal whitespace collapse with newline/tab preservation, length cap) - New deerflow.community.searx package: web_search, web_fetch, image_search backed by a private SearX instance, every external string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>> delimiters - All native community web providers (ddg_search, tavily, exa, firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail stubs that raise NativeWebToolDisabledError at import time, so a misconfigured tool.use path fails loud rather than silently falling back to unsanitized output - Native client back-doors (jina_client.py, infoquest_client.py) stubbed too - Native-tool tests quarantined under tests/_disabled_native/ (collect_ignore_glob via local conftest.py) - Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve newlines and tabs so list/table structure survives - Hardened runtime config.yaml references only the searx-backed tools - Factory overlay (backend/) kept in sync with deer-flow tree as a reference / source See HARDENING.md for the full audit trail and verification steps.
This commit is contained in:
13
deer-flow/backend/ruff.toml
Normal file
13
deer-flow/backend/ruff.toml
Normal file
@@ -0,0 +1,13 @@
|
||||
line-length = 240
|
||||
target-version = "py312"
|
||||
|
||||
[lint]
|
||||
select = ["E", "F", "I", "UP"]
|
||||
ignore = []
|
||||
|
||||
[lint.isort]
|
||||
known-first-party = ["deerflow", "app"]
|
||||
|
||||
[format]
|
||||
quote-style = "double"
|
||||
indent-style = "space"
|
||||
Reference in New Issue
Block a user