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.
86 lines
3.2 KiB
Python
86 lines
3.2 KiB
Python
"""Skill frontmatter validation utilities.
|
|
|
|
Pure-logic validation of SKILL.md frontmatter — no FastAPI or HTTP dependencies.
|
|
"""
|
|
|
|
import re
|
|
from pathlib import Path
|
|
|
|
import yaml
|
|
|
|
# Allowed properties in SKILL.md frontmatter
|
|
ALLOWED_FRONTMATTER_PROPERTIES = {"name", "description", "license", "allowed-tools", "metadata", "compatibility", "version", "author"}
|
|
|
|
|
|
def _validate_skill_frontmatter(skill_dir: Path) -> tuple[bool, str, str | None]:
|
|
"""Validate a skill directory's SKILL.md frontmatter.
|
|
|
|
Args:
|
|
skill_dir: Path to the skill directory containing SKILL.md.
|
|
|
|
Returns:
|
|
Tuple of (is_valid, message, skill_name).
|
|
"""
|
|
skill_md = skill_dir / "SKILL.md"
|
|
if not skill_md.exists():
|
|
return False, "SKILL.md not found", None
|
|
|
|
content = skill_md.read_text(encoding="utf-8")
|
|
if not content.startswith("---"):
|
|
return False, "No YAML frontmatter found", None
|
|
|
|
# Extract frontmatter
|
|
match = re.match(r"^---\n(.*?)\n---", content, re.DOTALL)
|
|
if not match:
|
|
return False, "Invalid frontmatter format", None
|
|
|
|
frontmatter_text = match.group(1)
|
|
|
|
# Parse YAML frontmatter
|
|
try:
|
|
frontmatter = yaml.safe_load(frontmatter_text)
|
|
if not isinstance(frontmatter, dict):
|
|
return False, "Frontmatter must be a YAML dictionary", None
|
|
except yaml.YAMLError as e:
|
|
return False, f"Invalid YAML in frontmatter: {e}", None
|
|
|
|
# Check for unexpected properties
|
|
unexpected_keys = set(frontmatter.keys()) - ALLOWED_FRONTMATTER_PROPERTIES
|
|
if unexpected_keys:
|
|
return False, f"Unexpected key(s) in SKILL.md frontmatter: {', '.join(sorted(unexpected_keys))}", None
|
|
|
|
# Check required fields
|
|
if "name" not in frontmatter:
|
|
return False, "Missing 'name' in frontmatter", None
|
|
if "description" not in frontmatter:
|
|
return False, "Missing 'description' in frontmatter", None
|
|
|
|
# Validate name
|
|
name = frontmatter.get("name", "")
|
|
if not isinstance(name, str):
|
|
return False, f"Name must be a string, got {type(name).__name__}", None
|
|
name = name.strip()
|
|
if not name:
|
|
return False, "Name cannot be empty", None
|
|
|
|
# Check naming convention (hyphen-case: lowercase with hyphens)
|
|
if not re.match(r"^[a-z0-9-]+$", name):
|
|
return False, f"Name '{name}' should be hyphen-case (lowercase letters, digits, and hyphens only)", None
|
|
if name.startswith("-") or name.endswith("-") or "--" in name:
|
|
return False, f"Name '{name}' cannot start/end with hyphen or contain consecutive hyphens", None
|
|
if len(name) > 64:
|
|
return False, f"Name is too long ({len(name)} characters). Maximum is 64 characters.", None
|
|
|
|
# Validate description
|
|
description = frontmatter.get("description", "")
|
|
if not isinstance(description, str):
|
|
return False, f"Description must be a string, got {type(description).__name__}", None
|
|
description = description.strip()
|
|
if description:
|
|
if "<" in description or ">" in description:
|
|
return False, "Description cannot contain angle brackets (< or >)", None
|
|
if len(description) > 1024:
|
|
return False, f"Description is too long ({len(description)} characters). Maximum is 1024 characters.", None
|
|
|
|
return True, "Skill is valid!", name
|