vector-memory-mcp: Agent for Claude Code

CONFIDENCE: 0.8 | INDUSTRY_ALIGNMENT: 0.8 | PRIORITY: high

Input validation sanitization

Input validation and sanitization for MCP tool parameters.

• validate-content: Content length ≤ 10K chars, strip dangerous patterns, validate encoding
• validate-category: Whitelist: code-solution, bug-fix, architecture, learning, tool-usage, debugging, performance, security, other
• validate-tags: Max 10 tags, alphanumeric + hyphens only, length 1-50 chars per tag
• validate-query: Non-empty string, max length, sanitize SQL-like patterns
• validate-limit: Integer range 1-50, prevent resource exhaustion
• validate-days: Positive integer, prevent invalid retention policies
• python-type-validation: Use Pydantic models, dataclass constraints, type hints for runtime validation

Path traversal prevention

Path traversal and directory escape attack prevention for file operations.

• working-directory-validation: Verify working_dir is absolute path, exists, and is accessible
• path-sanitization: Resolve absolute paths, normalize separators, validate no traversal sequences (../, .\)
• boundary-enforcement: Ensure all file operations stay within working_dir boundaries
• symbolic-link-check: Resolve symlinks and verify final path within allowed directory
• python-pattern: Use pathlib.Path.resolve(strict=True), os.path.commonpath() for validation

Injection attack prevention

SQL injection, command injection, and code injection prevention patterns.

• sql-injection: ALWAYS use parameterized queries with ? placeholders, NEVER string concatenation or f-strings in SQL
• command-injection: Avoid shell=True in subprocess, use argument lists instead of strings, sanitize all external inputs
• code-injection: Validate all dynamic imports, avoid eval/exec, sanitize template inputs
• python-sqlite-safety: Use cursor.execute(query, params) with tuples, never format strings into SQL
• content-hash-safety: Use SHA-256 for deduplication, handle hash collisions gracefully