DATA
6de0bf9f5b
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.
48 lines
1.6 KiB
Python
48 lines
1.6 KiB
Python
"""Shared utilities for skill-creator scripts."""
|
|
|
|
from pathlib import Path
|
|
|
|
|
|
|
|
def parse_skill_md(skill_path: Path) -> tuple[str, str, str]:
|
|
"""Parse a SKILL.md file, returning (name, description, full_content)."""
|
|
content = (skill_path / "SKILL.md").read_text()
|
|
lines = content.split("\n")
|
|
|
|
if lines[0].strip() != "---":
|
|
raise ValueError("SKILL.md missing frontmatter (no opening ---)")
|
|
|
|
end_idx = None
|
|
for i, line in enumerate(lines[1:], start=1):
|
|
if line.strip() == "---":
|
|
end_idx = i
|
|
break
|
|
|
|
if end_idx is None:
|
|
raise ValueError("SKILL.md missing frontmatter (no closing ---)")
|
|
|
|
name = ""
|
|
description = ""
|
|
frontmatter_lines = lines[1:end_idx]
|
|
i = 0
|
|
while i < len(frontmatter_lines):
|
|
line = frontmatter_lines[i]
|
|
if line.startswith("name:"):
|
|
name = line[len("name:"):].strip().strip('"').strip("'")
|
|
elif line.startswith("description:"):
|
|
value = line[len("description:"):].strip()
|
|
# Handle YAML multiline indicators (>, |, >-, |-)
|
|
if value in (">", "|", ">-", "|-"):
|
|
continuation_lines: list[str] = []
|
|
i += 1
|
|
while i < len(frontmatter_lines) and (frontmatter_lines[i].startswith(" ") or frontmatter_lines[i].startswith("\t")):
|
|
continuation_lines.append(frontmatter_lines[i].strip())
|
|
i += 1
|
|
description = " ".join(continuation_lines)
|
|
continue
|
|
else:
|
|
description = value.strip('"').strip("'")
|
|
i += 1
|
|
|
|
return name, description, content
|