""" Regex-based security pattern definitions for the security-guidance plugin. Pure data + one pure helper. No env-var reads, no I/O, no debug_log — kept side-effect-free so it can be imported in isolation. """ from enum import IntEnum _JS_EXTS = (".js", ".jsx", ".ts", ".tsx", ".mjs", ".cjs", ".mts", ".cts", ".vue", ".svelte") _PY_EXTS = (".py", ".pyi", ".ipynb") _DOC_EXTS = (".md", ".mdx", ".txt", ".rst", ".json", ".yaml", ".yml") _UNSAFE_DESERIALIZATION_REMINDER = """⚠️ Security Warning: Loading pickle data (or equivalents: cPickle, cloudpickle, dill, marshal, shelve, joblib, pandas.read_pickle, numpy with allow_pickle=True) from untrusted sources allows arbitrary code execution. For simple data, prefer JSON or msgspec. For typed objects, prefer a schema-validated deserializer (msgspec.Struct, pydantic, marshmallow) that constructs only declared types. If this is safe or is explicitly needed, briefly document that in a comment before continuing.""" _UNSAFE_YAML_LOAD_REMINDER = """⚠️ Security Warning: yaml.load() / yaml.unsafe_load() execute arbitrary Python via !!python/object tags. Use yaml.safe_load() if the file only contains simple data structures (dicts, lists, strings, numbers). If you need typed objects, parse with safe_load and validate the result against a schema (pydantic, msgspec, marshmallow) — never use a custom Loader that constructs arbitrary types.""" _UNSAFE_TORCH_LOAD_REMINDER = """⚠️ Security Warning: torch.load() defaults to weights_only=False, which unpickles arbitrary Python objects and allows arbitrary code execution. If the file only contains tensors and simple data structures, pass weights_only=True (or set TORCH_FORCE_WEIGHTS_ONLY_LOAD=1).""" def _call_args(): """Regex for the arguments of one call, read from just after its "(". Steps over strings, comments and up to three levels of nested brackets as units, across lines, so text that follows it is an argument of this call: not of a nested one, not part of a comment, and not past the closing bracket. Each alternative starts with a different character and every repeat is bounded, so it cannot backtrack badly. """ char = r"[^()\x22\x27#]" string = r"\x22(?:[^\x22\\\n]|\\.){0,300}\x22|\x27(?:[^\x27\\\n]|\\.){0,300}\x27" comment = r"#[^\n]{0,300}\n" leaf = rf"{char}|{string}|{comment}" group = rf"\((?:{leaf}){{0,200}}\)" for _ in range(2): group = rf"\((?:{leaf}|{group}){{0,200}}\)" return rf"(?:{leaf}|{group}){{0,400}}" _CALL_ARGS = _call_args() def _page_function_call(): """Regex for Playwright's and Puppeteer's `$eval('selector', function`, read from its "eval(". It runs the function, so nothing is evaluated from a string. Both have to be written out in the call: a string with nothing put into it, then a function. AngularJS `scope.$eval(expr)` and any other `$eval(` do not match. Every repeat is bounded. """ selector = r"\x22[^\x22\\\n]{0,300}\x22|\x27[^\x27\\\n]{0,300}\x27|`[^`$\\]{0,300}`" arrow = r"(?:[\w$]{1,60}|\([^()]{0,200}\))\s{0,20}(?::[^=\n]{0,60})?=>" return rf"eval\(\s{{0,200}}(?:{selector})\s{{0,20}},\s{{0,200}}(?:async\b\s{{0,20}})?(?:function\b|{arrow})" _PAGE_FUNCTION_CALL = _page_function_call() # Security patterns configuration SECURITY_PATTERNS = [ { "ruleName": "github_actions_workflow", "path_check": lambda path: ".github/workflows/" in path and (path.endswith(".yml") or path.endswith(".yaml")), "reminder": """⚠️ Security Warning: You are editing a GitHub Actions workflow file. Be aware of these security risks: 1. **Command Injection**: Never use untrusted input (like issue titles, PR descriptions, commit messages) directly in run: commands without proper escaping 2. **Use environment variables**: Instead of ${{ github.event.issue.title }}, use env: with proper quoting 3. **Review the guide**: https://github.blog/security/vulnerability-research/how-to-catch-github-actions-workflow-injections-before-attackers-do/ Example of UNSAFE pattern to avoid: run: echo "${{ github.event.issue.title }}" Example of SAFE pattern: env: TITLE: ${{ github.event.issue.title }} run: echo "$TITLE" Other risky inputs to be careful with: - github.event.issue.body - github.event.pull_request.title - github.event.pull_request.body - github.event.comment.body - github.event.review.body - github.event.review_comment.body - github.event.pages.*.page_name - github.event.commits.*.message - github.event.head_commit.message - github.event.head_commit.author.email - github.event.head_commit.author.name - github.event.commits.*.author.email - github.event.commits.*.author.name - github.event.pull_request.head.ref - github.event.pull_request.head.label - github.event.pull_request.head.repo.default_branch - github.event.client_payload.* (repository_dispatch events — attacker can set any field) 4. **Ref injection**: Never use untrusted input in `ref:` parameters of `actions/checkout`. For `client_payload.pr_number`, validate it matches `^[0-9]+$` before using in `ref: refs/pull/${{ ... }}/head` - github.head_ref""", }, { "ruleName": "child_process_exec", # Gate to JS/TS files — bare `exec(` otherwise fires on Python's # exec() and on prose/docstrings mentioning exec. "path_filter": lambda p: p.endswith(_JS_EXTS), "substrings": ["child_process.exec", "execSync("], "regex": r"(? o[k], root); for computation use a safe expression parser. NEVER interpolate untrusted strings into new Function() bodies.", }, { "ruleName": "eval_injection", # Lookbehind excludes `.` so method calls like PyTorch model.eval(), # redis.eval(), spec.eval() don't match. Playwright's page.$eval('selector', # function) is left out too. Skip doc/prose files. "path_filter": lambda p: not p.endswith(_DOC_EXTS), "regex": rf"(?]{0,400}integrity\s*=)" r"[^>]{0,200}src\s*=\s*[\x22\x27](?:https?:)?//" r"[^\x22\x27]{1,300}[\x22\x27]" r"[^>]{0,100}>" ), "reminder": '⚠️ Security Warning: Add integrity="sha384-..." crossorigin="anonymous" to external script tags. Loading scripts without Subresource Integrity exposes you to CDN compromise.', }, { "ruleName": "torch_unsafe_load", # Suppressed by weights_only=True among the call's own arguments. weights_only=False # still triggers. "regex": ( r"(?:\btorch\.load|\.torch_load)\s*\(" rf"(?![^)\n]{{0,200}}weights_only\s*=\s*True|{_CALL_ARGS}\bweights_only\s*=\s*True)" ), "reminder": _UNSAFE_TORCH_LOAD_REMINDER, }, { "ruleName": "yaml_unsafe_load_variants", # yaml.unsafe_load (stdlib alias) plus unsafe wrapper method names seen in the wild. # Bare yaml.load() is unsafe_yaml_load's job (RuleId 12). "regex": r"(?:\byaml\.unsafe_load|\.yaml_unsafe_load)\s*\(", "reminder": _UNSAFE_YAML_LOAD_REMINDER, }, { "ruleName": "pickle_wrapper_load", # Library APIs that unpickle without saying "pickle". numpy.load only triggers # when allow_pickle=True is explicit (defaults to False since numpy 1.16.3). "regex": ( r"\bjoblib\.load\s*\(|\b(?:pd|pandas)\.read_pickle\s*\(|\.cloudpickle_load\s*\(" rf"|\b(?:np|numpy)\.load\s*\((?:[^)\n]{{0,200}}|{_CALL_ARGS}\b)allow_pickle\s*=\s*True" ), "reminder": _UNSAFE_DESERIALIZATION_REMINDER, }, ] class RuleId(IntEnum): """ Stable numeric IDs for SECURITY_PATTERNS rules, emitted via the PostToolUse metrics field so telemetry can attribute pattern-warning events to specific checks. The metrics schema only allows bool|number values (no strings), so rule names can't be sent directly. Values are frozen: do not renumber existing entries. Append new ones. """ GITHUB_ACTIONS_WORKFLOW = 1 CHILD_PROCESS_EXEC = 2 NEW_FUNCTION_INJECTION = 3 EVAL_INJECTION = 4 REACT_DANGEROUSLY_SET_HTML = 5 DOCUMENT_WRITE_XSS = 6 INNERHTML_XSS = 7 PICKLE_DESERIALIZATION = 8 OS_SYSTEM_INJECTION = 9 PYTHON_SUBPROCESS_SHELL = 10 GO_EXEC_SHELL_INJECTION = 11 UNSAFE_YAML_LOAD = 12 NODE_CREATECIPHER_NO_IV = 13 AES_ECB_MODE = 14 TLS_VERIFICATION_DISABLED = 15 MARSHAL_LOADS = 16 SHELVE_OPEN = 17 XML_UNSAFE_PARSE = 18 PICKLE_VARIANTS_LOAD = 19 OUTERHTML_XSS = 20 INSERTADJACENTHTML_XSS = 21 SCRIPT_SRC_WITHOUT_SRI = 22 TORCH_UNSAFE_LOAD = 23 YAML_UNSAFE_LOAD_VARIANTS = 24 PICKLE_WRAPPER_LOAD = 25 _RULE_NAME_TO_ID = { "github_actions_workflow": RuleId.GITHUB_ACTIONS_WORKFLOW, "child_process_exec": RuleId.CHILD_PROCESS_EXEC, "new_function_injection": RuleId.NEW_FUNCTION_INJECTION, "eval_injection": RuleId.EVAL_INJECTION, "react_dangerously_set_html": RuleId.REACT_DANGEROUSLY_SET_HTML, "document_write_xss": RuleId.DOCUMENT_WRITE_XSS, "innerHTML_xss": RuleId.INNERHTML_XSS, "pickle_deserialization": RuleId.PICKLE_DESERIALIZATION, "os_system_injection": RuleId.OS_SYSTEM_INJECTION, "python_subprocess_shell": RuleId.PYTHON_SUBPROCESS_SHELL, "go_exec_shell_injection": RuleId.GO_EXEC_SHELL_INJECTION, "unsafe_yaml_load": RuleId.UNSAFE_YAML_LOAD, "node_createcipher_no_iv": RuleId.NODE_CREATECIPHER_NO_IV, "aes_ecb_mode": RuleId.AES_ECB_MODE, "tls_verification_disabled": RuleId.TLS_VERIFICATION_DISABLED, "marshal_loads": RuleId.MARSHAL_LOADS, "shelve_open": RuleId.SHELVE_OPEN, "xml_unsafe_parse": RuleId.XML_UNSAFE_PARSE, "pickle_variants_load": RuleId.PICKLE_VARIANTS_LOAD, "outerHTML_xss": RuleId.OUTERHTML_XSS, "insertAdjacentHTML_xss": RuleId.INSERTADJACENTHTML_XSS, "script_src_without_sri": RuleId.SCRIPT_SRC_WITHOUT_SRI, "torch_unsafe_load": RuleId.TORCH_UNSAFE_LOAD, "yaml_unsafe_load_variants": RuleId.YAML_UNSAFE_LOAD_VARIANTS, "pickle_wrapper_load": RuleId.PICKLE_WRAPPER_LOAD, } # Fail loudly at import time if a pattern is added without a RuleId. # This fires in pytest on every PR, so desync is caught before merge. assert set(_RULE_NAME_TO_ID) == {p["ruleName"] for p in SECURITY_PATTERNS}, ( f"RuleId enum out of sync with SECURITY_PATTERNS: " f"missing={set(p['ruleName'] for p in SECURITY_PATTERNS) - set(_RULE_NAME_TO_ID)}, " f"extra={set(_RULE_NAME_TO_ID) - set(p['ruleName'] for p in SECURITY_PATTERNS)}" ) def rule_names_to_mask(rule_names): """Pack a set of rule names into a bitmask. Bit N set means RuleId(N) matched. User-defined patterns (rule_name starting with "user:") have no static RuleId and are excluded from the mask.""" mask = 0 for name in rule_names: if name in _RULE_NAME_TO_ID: mask |= 1 << _RULE_NAME_TO_ID[name] return mask