diff --git a/internal/engines/wikipedia.go b/internal/engines/wikipedia.go index bbf1222..f29ff74 100644 --- a/internal/engines/wikipedia.go +++ b/internal/engines/wikipedia.go @@ -33,6 +33,44 @@ type WikipediaEngine struct { client *http.Client } +// validWikipediaLangs contains the set of valid Wikipedia language codes. +// This prevents SSRF attacks where an attacker could use a malicious language +// value to redirect requests to an attacker-controlled domain. +var validWikipediaLangs = map[string]struct{}{ + "aa": {}, "ab": {}, "ae": {}, "af": {}, "ak": {}, "am": {}, "an": {}, + "ar": {}, "arc": {}, "as": {}, "ast": {}, "at": {}, "av": {}, "ay": {}, + "az": {}, "ba": {}, "be": {}, "bg": {}, "bh": {}, "bi": {}, "bm": {}, + "bn": {}, "bo": {}, "br": {}, "bs": {}, "ca": {}, "ce": {}, "ch": {}, + "co": {}, "cr": {}, "cs": {}, "cu": {}, "cv": {}, "cy": {}, "da": {}, + "de": {}, "di": {}, "dv": {}, "dz": {}, "ee": {}, "el": {}, "en": {}, + "eo": {}, "es": {}, "et": {}, "eu": {}, "fa": {}, "ff": {}, "fi": {}, + "fj": {}, "fo": {}, "fr": {}, "fy": {}, "ga": {}, "gd": {}, "gl": {}, + "gn": {}, "gu": {}, "gv": {}, "ha": {}, "he": {}, "hi": {}, "ho": {}, + "hr": {}, "ht": {}, "hu": {}, "hy": {}, "hz": {}, "ia": {}, "id": {}, + "ie": {}, "ig": {}, "ii": {}, "ik": {}, "io": {}, "is": {}, "it": {}, + "iu": {}, "ja": {}, "jv": {}, "ka": {}, "kg": {}, "ki": {}, "kj": {}, + "kk": {}, "kl": {}, "km": {}, "kn": {}, "ko": {}, "kr": {}, "ks": {}, + "ku": {}, "kv": {}, "kw": {}, "ky": {}, "la": {}, "lb": {}, "lg": {}, + "li": {}, "lij": {}, "ln": {}, "lo": {}, "lt": {}, "lv": {}, "mg": {}, + "mh": {}, "mi": {}, "mk": {}, "ml": {}, "mn": {}, "mo": {}, "mr": {}, + "ms": {}, "mt": {}, "mus": {}, "my": {}, "na": {}, "nah": {}, "nap": {}, + "nd": {}, "nds": {}, "ne": {}, "new": {}, "ng": {}, "nl": {}, "nn": {}, + "no": {}, "nov": {}, "nrm": {}, "nv": {}, "ny": {}, "oc": {}, "oj": {}, + "om": {}, "or": {}, "os": {}, "pa": {}, "pag": {}, "pam": {}, "pap": {}, + "pdc": {}, "pl": {}, "pms": {}, "pn": {}, "ps": {}, "pt": {}, "qu": {}, + "rm": {}, "rmy": {}, "rn": {}, "ro": {}, "roa-rup": {}, "ru": {}, + "rw": {}, "sa": {}, "sah": {}, "sc": {}, "scn": {}, "sco": {}, "sd": {}, + "se": {}, "sg": {}, "sh": {}, "si": {}, "simple": {}, "sk": {}, "sl": {}, + "sm": {}, "sn": {}, "so": {}, "sq": {}, "sr": {}, "ss": {}, "st": {}, + "su": {}, "sv": {}, "sw": {}, "szl": {}, "ta": {}, "te": {}, "tg": {}, + "th": {}, "ti": {}, "tk": {}, "tl": {}, "tn": {}, "to": {}, "tpi": {}, + "tr": {}, "ts": {}, "tt": {}, "tum": {}, "tw": {}, "ty": {}, "udm": {}, + "ug": {}, "uk": {}, "ur": {}, "uz": {}, "ve": {}, "vec": {}, "vi": {}, + "vls": {}, "vo": {}, "wa": {}, "wo": {}, "xal": {}, "xh": {}, "yi": {}, + "yo": {}, "za": {}, "zea": {}, "zh": {}, "zh-classical": {}, + "zh-min-nan": {}, "zh-yue": {}, "zu": {}, +} + func (e *WikipediaEngine) Name() string { return "wikipedia" } func (e *WikipediaEngine) Search(ctx context.Context, req contracts.SearchRequest) (contracts.SearchResponse, error) { @@ -50,6 +88,11 @@ func (e *WikipediaEngine) Search(ctx context.Context, req contracts.SearchReques // Wikipedia subdomains are based on the language code; keep it simple for MVP. lang = strings.SplitN(lang, "-", 2)[0] lang = strings.ReplaceAll(lang, "_", "-") + // Validate lang against whitelist to prevent SSRF attacks where an attacker + // could use a malicious language value to redirect requests to their server. + if _, ok := validWikipediaLangs[lang]; !ok { + lang = "en" + } wikiNetloc := fmt.Sprintf("%s.wikipedia.org", lang) endpoint := fmt.Sprintf(