--- a/http-git.nse 2012-12-11 14:40:29.323507491 -0600 +++ b/http-git.nse 2012-12-11 14:34:32.297737214 -0600 @@ -13,9 +13,33 @@ -- | BitBucket remote: AlexWebr/nse (accessed over HTTP, pull-only) -- |_ Based on the file '.gitignore', this is a Ruby on Rails application -- --- Version 1.1 --- Created 27 June 2012 - written by Alex Weber - +-- @xmloutput +-- [...snip...] +-- +--
+-- http://github.com/anotherperson/anotherepo +--
+-- +--
+-- JBoss Java web application +-- Java application +--
+-- +-- A nice repository +-- +-- false +-- true +-- true +-- true +-- false +--
+-- +--
+-- passw +--
+-- +-- +-- [...snip...] local http = require("http") local shortport = require("shortport") @@ -32,12 +56,12 @@ portrule = shortport.http local STATUS_OK = 200 -- We consider 200 to mean "okay, file exists and we received its contents" +-- Long strings (like a repository's description) will be truncated to this +-- number of characters in normal output. +local TRUNC_LENGTH = 60 function action(host, port) - -- All methods that we call on this table will be from the table library - local out = {} - setmetatable(out, {__index = table}) - local repos_found = 0 + local out -- We can accept a single root, or a table of roots to try local root_arg = stdnse.get_script_args("http-git.root") @@ -68,10 +92,7 @@ -- We could try for /.git/, but we will not get a 200 if directory -- listings are disallowed. if http.get(host, port, root .. ".git/HEAD").status == STATUS_OK then - if repos_found > 0 then - out:insert("") - end - repos_found = repos_found + 1 + out = out or {} local replies = {} -- This function returns true if we got a 200 OK when -- fetching 'filename' from the server @@ -90,7 +111,6 @@ ".gitignore", } - local count = { ok = 0, tried = 0 } local prequests = {} -- prequests = pipelined requests (temp) -- Go through all of the filenames and do an HTTP GET for _, name in ipairs(repo) do -- for every filename @@ -104,83 +124,43 @@ end for i, reply in ipairs(replies) do - count.tried = count.tried + 1 -- We want this to be indexed by filename, not an integer, so we convert it -- We added to the pipeline in the same order as the filenames, so this is safe replies[repo[i]] = reply -- create index by filename replies[i] = nil -- delete integer-indexed entry - if reply.status == STATUS_OK then count.ok = count.ok + 1 end end - -- Tell the user that we found a repository, and indicate if - -- we didn't find all the files we were looking for. + -- Mark each file that we tried to get as 'found' (true) or 'not found' (false). local location = host.ip .. ":" .. port.number .. root .. ".git/" - if count.ok == count.tried then - out:insert("Git repository found at " .. location) - else -- if we didn't find all the files we were hoping to, we might not actually have a repo - out:insert("Potential Git repository found at " .. location .. " (found " .. - tostring(count.ok + 1) .. " of " .. tostring(count.tried + 1) .. " expected files)") - -- we already got /.git/HEAD, so add one to 'found' and 'expected' - end - - -- This function matches a table of words/regexes against a single string - -- This function is used immediately after it is declared - local function match_many(str, table_of_words) - local matched_string, lstr, t_to_return = false, string.lower(str), {} - for i, word in ipairs(table_of_words) do - matched_string = string.match(lstr, word) - if matched_string then table.insert(t_to_return , matched_string) end - end - return t_to_return - end - - -- Look through all the repo files we grabbed and see if we can find anything interesting - local interesting = { "bug", "passw", "pw", "user", "uid", "key", "secret" } - for name, reply in pairs(replies) do - if ok(name) then -- for all replies that were successful - local found_anything = false -- have we found anything yet? - local buf = strbuf.new() - for _, matched in ipairs(match_many(reply.body:lower(), interesting)) do -- match all files against 'interesting' - if not found_anything then -- if this is our first find, print filename and stuff - buf = (((((buf .. "Contents of '") .. name) .. "' matched patterns '") .. matched) .. "'") -- the '..' is right-associative :( - found_anything = true - else - buf = ((buf .. ", '" .. matched) .. "'") - end -- if we found something already, tack this pattern onto the end - end -- If we matched anything, finish the line up - if found_anything then - buf = buf .. " (case-insensitive match)" - out:insert(strbuf.dump(buf)) + out[location] = {} + -- A nice shortcut + local loc = out[location] + loc["files-found"] = {} + for name, _ in pairs(replies) do + loc["files-found"][name] = ok(name) + end + + -- Look through all the repo files we grabbed and see if we can find anything interesting. + local interesting = { "bug", "key", "passw", "pw", "user", "secret", "uid" } + for name, reply in pairs(replies) do + if ok(name) then + for _, pattern in ipairs(interesting) do + if string.match(reply.body, pattern) then + -- A Lua idiom - don't create this table until we actually have something to put in it + loc["interesting-matches"] = loc["interesting-matches"] or {} + loc["interesting-matches"][name] = loc["interesting-matches"][name] or {} + table.insert(loc["interesting-matches"][name], pattern) + end end end end - -- Given a longer plain-text string (a large text file, for example), append - -- a summary of it (the first 60 characters or the first line, whichever is shorter) - local function append_short_version(description, original_string) - local short = string.sub(original_string, 1, 60) -- trim the string first, in case it is huge - -- We try to cut off the newline if we can - local no_newline = string.match(short, "(.-)\r?\n") -- we don't want such an open-ended regex on a potentially huge string - local s = no_newline or short - if #original_string > #s then - -- If we cut off something, we want to put an ellipsis on the end - s = description .. ": " .. s .. "..." - else - s = description .. ": " .. s - end - out:insert(s) + if ok(".git/COMMIT_EDITMSG") then + loc["last-commit-message"] = replies[".git/COMMIT_EDITMSG"].body end - -- Get the first line and trim to 60 characters, if we got a COMMIT_EDITMESSAGE - if ok(".git/COMMIT_EDITMSG") then - -- If there's no newline in the file (there usually is), this won't work. - -- Normally, it's a commit message followed by a bunch of commented-out lines (#). - append_short_version("Last commit message", replies[".git/COMMIT_EDITMSG"].body) - end - - -- Do the same thing as for description - get first line, truncate to 60 characters. if ok(".git/description") then - append_short_version("Repository description", replies[".git/description"].body) + loc["repository-description"] = replies[".git/description"].body end -- If we got /.git/config, we might find out things like the user's GitHub name, @@ -197,23 +177,9 @@ table.insert(remotes, url) end - -- These are some popular / well-known Git hosting services and/or hosting services - -- that allow deployment via 'git push' - local popular_remotes = { - ["github.com"] = "Source might be at https://github.com/", - ["gitorious.com"] = "Source might be at https://gitorious.com/", - ["bitbucket.org"] = "Source might be at https://bitbucket.org/", - ["heroku.com"] = "App might be deployed to http://.herokuapp.com", - } for _, url in ipairs(remotes) do - out:insert("Remote: " .. url) - local domain, reponame = string.match(url, "[@/]([%w._-]+)[:/]([%w._-]+/?[%w._-]+)") - local extrainfo = popular_remotes[domain] - -- Try and cut off the '.git' extension - reponame = string.match(reponame, "(.+)%.git") or reponame - if extrainfo then - out:insert(" -> " .. string.gsub(extrainfo, "", reponame)) - end + loc["remotes"] = loc["remotes"] or {} + table.insert(loc["remotes"], url) end end @@ -242,16 +208,17 @@ { "%.class", "Java application" }, { "%.php", "PHP application" }, } - local excludefile_that_matched = nil - local app = nil - -- We check every file against every fingerprint + -- The XML produced here is divided by ignorefile and is sorted from first to last + -- in order of specificity. e.g. All JBoss applications are Java applications, + -- but not all Java applications are JBoss. In that case, JBoss and Java will + -- be output, but JBoss will be listed first. for _, file in ipairs(ignorefiles) do - if ok(file) then -- we only test all fingerprints if we got the file - for i, fingerprint in ipairs(fingerprints) do + if ok(file) then -- We only test all fingerprints if we got the file. + for _, fingerprint in ipairs(fingerprints) do if string.match(replies[file].body, fingerprint[1]) then - out:insert("Based on the file '" .. file .. "', this is a " .. fingerprint[2]) - -- Based on the file '.gitignore', this is a Ruby on Rails application" - break -- we only want to print our first guess (the most specific one that matched) + loc["project-type"] = loc["project-type"] or {} + loc["project-type"][file] = loc["project-type"][file] or {} + table.insert(loc["project-type"][file], fingerprint[2]) end end end @@ -259,7 +226,86 @@ end end - -- Replace non-printing characters with asterisks - if #out > 0 then return stdnse.format_output(true, out) - else return nil end + -- If we didn't get anything, we return early. No point doing the + -- normal formatting! + if out == nil then + return nil + end + + -- Truncate to TRUNC_LENGTH characters and replace control characters (newlines, etc) with spaces. + local function summarize(str) + str = stdnse.string_or_blank(str, "") + local original_length = #str + str = string.sub(str, 1, TRUNC_LENGTH) + str = string.gsub(str, "%c", " ") + if original_length > TRUNC_LENGTH then + str = str .. "..." + end + return str + end + + -- We convert the full output to pretty output for -oN + local normalout + for location, info in pairs(out) do + normalout = normalout or {} + -- This table gets converted to a string format_output, and then inserted into the 'normalout' table + local new = {} + -- Headings for each place we found a repo + new["name"] = location + + -- How sure are we that this is a Git repository? + local count = { tried = 0, ok = 0 } + for _, found in pairs(info["files-found"]) do + count.tried = count.tried + 1 + if found then count.ok = count.ok + 1 end + end + + -- If 3 or more of the files we were looking for are not on the server, + -- we are less confident that we got a real Git repository + if count.tried - count.ok <= 2 then + table.insert(new, "Git repository found!") + else -- We already got .git/HEAD, so we add 1 to 'tried' and 'ok' + table.insert(new, "Potential Git repository found (found " .. (count.ok + 1) .. "/" .. (count.tried + 1) .. " expected files)") + end + + -- Show what patterns matched what files + for name, matches in pairs(info["interesting-matches"] or {}) do + local temp = name .. " matched patterns" + for _, matched in ipairs(matches) do + temp = temp .. " '" .. matched .. "'" + end + table.insert(new, temp) + end + + if info["repository-description"] then + table.insert(new, "Repository description: " .. summarize(info["repository-description"])) + end + + if info["last-commit-message"] then + table.insert(new, "Last commit message: " .. summarize(info["last-commit-message"])) + end + + -- If we found any remotes in .git/config, process them now + if info["remotes"] then + local old_name = info["remotes"]["name"] -- in case 'name' is a remote + info["remotes"]["name"] = "Remotes:" + -- Remove the newline from format_output's output - it looks funny with it + local temp = string.gsub(stdnse.format_output(true, info["remotes"]), "^\n", "") + -- using 'temp' here because gsub() has multiple return values that insert() will try + -- to use, and I don't know of a better way to prevent that ;) + table.insert(new, temp) + info["remotes"]["name"] = old_name + end + + -- Take the first guessed project type from each ignorefile + if info["project-type"] then + for name, types in pairs(info["project-type"]) do + table.insert(new, "Project type: " .. types[1] .. " (guessed from " .. name .. ")") + end + end + -- Insert this location's information. + table.insert(normalout, new) + end + + return out, stdnse.format_output(true, normalout) end