{{ message }}
Repository navigation
Expand file tree
/
Copy pathartifact-scanner.ts
More file actions
430 lines (389 loc) · 11.9 KB
/
Copy pathartifact-scanner.ts
File metadata and controls
430 lines (389 loc) · 11.9 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
import * as fs from "fs";
import * as os from "os";
import * as path from "path";
import * as exec from "@actions/exec";
import { Logger } from "./logging";
import { getErrorMessage } from "./util";
/**
* Enumerates known types of GitHub token formats.
*/
export enum TokenType {
PersonalAccessClassic = "Personal Access Token (Classic)",
PersonalAccessFineGrained = "Personal Access Token (Fine-grained)",
OAuth = "OAuth Access Token",
UserToServer = "User-to-Server Token",
ServerToServer = "Server-to-Server Token",
Refresh = "Refresh Token",
AppInstallationAccess = "App Installation Access Token",
}
/** A value of this type associates a token type with its pattern. */
export interface TokenPattern {
type: TokenType;
pattern: RegExp;
}
/** The pattern for PATs (Classic) */
export const GITHUB_PAT_CLASSIC_PATTERN: TokenPattern = {
type: TokenType.PersonalAccessClassic,
pattern: /\bghp_[a-zA-Z0-9]{36}\b/g,
};
/** The pattern for PATs (Fine-grained) */
export const GITHUB_PAT_FINE_GRAINED_PATTERN: TokenPattern = {
type: TokenType.PersonalAccessFineGrained,
pattern: /\bgithub_pat_[a-zA-Z0-9_]+\b/g,
};
/**
* GitHub token patterns to scan for.
* These patterns match various GitHub token formats.
*/
const GITHUB_TOKEN_PATTERNS: TokenPattern[] = [
GITHUB_PAT_CLASSIC_PATTERN,
GITHUB_PAT_FINE_GRAINED_PATTERN,
{
type: TokenType.OAuth,
pattern: /\bgho_[a-zA-Z0-9]{36}\b/g,
},
{
type: TokenType.UserToServer,
pattern: /\bghu_[a-zA-Z0-9]{36}\b/g,
},
{
type: TokenType.ServerToServer,
pattern: /\bghs_[a-zA-Z0-9]{36}\b/g,
},
{
type: TokenType.Refresh,
pattern: /\bghr_[a-zA-Z0-9]{36}\b/g,
},
{
type: TokenType.AppInstallationAccess,
pattern: /\bghs_[a-zA-Z0-9]{255}\b/g,
},
];
interface TokenFinding {
tokenType: string;
filePath: string;
}
interface ScanResult {
scannedFiles: number;
findings: TokenFinding[];
}
/**
* Checks whether `value` matches any token `patterns`.
* @param value The value to match against.
* @param patterns The patterns to check.
* @returns The type of the first matching pattern, or `undefined` if none match.
*/
export function isAuthToken(
value: string,
patterns: TokenPattern[] = GITHUB_TOKEN_PATTERNS,
) {
for (const { type, pattern } of patterns) {
if (value.match(pattern)) {
return type;
}
}
return undefined;
}
/**
* Scans a file for GitHub tokens.
*
* @param filePath Path to the file to scan
* @param relativePath Relative path for display purposes
* @param logger Logger instance
* @returns Array of token findings in the file
*/
function scanFileForTokens(
filePath: string,
relativePath: string,
logger: Logger,
): TokenFinding[] {
const findings: TokenFinding[] = [];
try {
const content = fs.readFileSync(filePath, "utf8");
for (const { type, pattern } of GITHUB_TOKEN_PATTERNS) {
const matches = content.match(pattern);
if (matches) {
for (let i = 0; i < matches.length; i++) {
findings.push({ tokenType: type, filePath: relativePath });
}
logger.debug(`Found ${matches.length} ${type}(s) in ${relativePath}`);
}
}
return findings;
} catch (e) {
// If we can't read the file as text, it's likely binary or inaccessible
logger.debug(
`Could not scan file ${filePath} for tokens: ${getErrorMessage(e)}`,
);
return [];
}
}
/**
* Recursively extracts and scans archive files (.zip, .gz, .tar.gz).
*
* @param archivePath Path to the archive file
* @param relativeArchivePath Relative path of the archive for display
* @param extractDir Directory to extract to
* @param logger Logger instance
* @param depth Current recursion depth (to prevent infinite loops)
* @returns Scan results
*/
async function scanArchiveFile(
archivePath: string,
relativeArchivePath: string,
extractDir: string,
logger: Logger,
depth: number = 0,
): Promise<ScanResult> {
const MAX_DEPTH = 10; // Prevent infinite recursion
if (depth > MAX_DEPTH) {
throw new Error(
`Maximum archive extraction depth (${MAX_DEPTH}) reached for ${archivePath}`,
);
}
if (process.platform === "win32") {
throw new Error("Scanning archives is not supported on Windows.");
}
const result: ScanResult = {
scannedFiles: 0,
findings: [],
};
try {
const tempExtractDir = fs.mkdtempSync(
path.join(extractDir, `extract-${depth}-`),
);
// Determine archive type and extract accordingly
const fileName = path.basename(archivePath).toLowerCase();
if (fileName.endsWith(".tar.gz") || fileName.endsWith(".tgz")) {
// Extract tar.gz files
logger.debug(`Extracting tar.gz file: ${archivePath}`);
await exec.exec("tar", ["-xzf", archivePath, "-C", tempExtractDir], {
silent: true,
});
} else if (fileName.endsWith(".tar.zst")) {
// Extract tar.zst files
logger.debug(`Extracting tar.zst file: ${archivePath}`);
await exec.exec(
"tar",
["--zstd", "-xf", archivePath, "-C", tempExtractDir],
{
silent: true,
},
);
} else if (fileName.endsWith(".zst")) {
// Extract .zst files (single file compression)
logger.debug(`Extracting zst file: ${archivePath}`);
const outputFile = path.join(
tempExtractDir,
path.basename(archivePath, ".zst"),
);
await exec.exec("zstd", ["-d", archivePath, "-o", outputFile], {
silent: true,
});
} else if (fileName.endsWith(".gz")) {
// Extract .gz files (single file compression)
logger.debug(`Extracting gz file: ${archivePath}`);
const outputFile = path.join(
tempExtractDir,
path.basename(archivePath, ".gz"),
);
await exec.exec("gunzip", ["-c", archivePath], {
outStream: fs.createWriteStream(outputFile),
silent: true,
});
} else if (fileName.endsWith(".zip")) {
// Extract zip files
logger.debug(`Extracting zip file: ${archivePath}`);
await exec.exec(
"unzip",
["-q", "-o", archivePath, "-d", tempExtractDir],
{
silent: true,
},
);
}
// Scan the extracted contents
const scanResult = await scanDirectory(
tempExtractDir,
relativeArchivePath,
logger,
depth + 1,
);
result.scannedFiles += scanResult.scannedFiles;
result.findings.push(...scanResult.findings);
// Clean up extracted files
fs.rmSync(tempExtractDir, { recursive: true, force: true });
} catch (e) {
logger.debug(
`Could not extract or scan archive file ${archivePath}: ${getErrorMessage(e)}`,
);
}
return result;
}
/**
* Scans a single file, including recursive archive extraction if applicable.
*
* @param fullPath Full path to the file
* @param relativePath Relative path for display
* @param extractDir Directory to use for extraction (for archive files)
* @param logger Logger instance
* @param depth Current recursion depth
* @returns Scan results
*/
async function scanFile(
fullPath: string,
relativePath: string,
extractDir: string,
logger: Logger,
depth: number = 0,
): Promise<ScanResult> {
const result: ScanResult = {
scannedFiles: 1,
findings: [],
};
// Check if it's an archive file and recursively scan it
const fileName = path.basename(fullPath).toLowerCase();
const isArchive =
fileName.endsWith(".zip") ||
fileName.endsWith(".tar.gz") ||
fileName.endsWith(".tgz") ||
fileName.endsWith(".tar.zst") ||
fileName.endsWith(".zst") ||
fileName.endsWith(".gz");
if (isArchive) {
const archiveResult = await scanArchiveFile(
fullPath,
relativePath,
extractDir,
logger,
depth,
);
result.scannedFiles += archiveResult.scannedFiles;
result.findings.push(...archiveResult.findings);
}
// Scan the file itself for tokens (unless it's a pure binary archive format)
const fileFindings = scanFileForTokens(fullPath, relativePath, logger);
result.findings.push(...fileFindings);
return result;
}
/**
* Recursively scans a directory for GitHub tokens.
*
* @param dirPath Directory path to scan
* @param baseRelativePath Base relative path for computing display paths
* @param logger Logger instance
* @param depth Current recursion depth
* @returns Scan results
*/
async function scanDirectory(
dirPath: string,
baseRelativePath: string,
logger: Logger,
depth: number = 0,
): Promise<ScanResult> {
const result: ScanResult = {
scannedFiles: 0,
findings: [],
};
const entries = fs.readdirSync(dirPath, { withFileTypes: true });
for (const entry of entries) {
const fullPath = path.join(dirPath, entry.name);
const relativePath = path.join(baseRelativePath, entry.name);
if (entry.isDirectory()) {
const subResult = await scanDirectory(
fullPath,
relativePath,
logger,
depth,
);
result.scannedFiles += subResult.scannedFiles;
result.findings.push(...subResult.findings);
} else if (entry.isFile()) {
const fileResult = await scanFile(
fullPath,
relativePath,
path.dirname(fullPath),
logger,
depth,
);
result.scannedFiles += fileResult.scannedFiles;
result.findings.push(...fileResult.findings);
}
}
return result;
}
/**
* Scans a list of files and directories for GitHub tokens.
* Recursively extracts and scans archive files (.zip, .gz, .tar.gz).
*
* @param filesToScan List of file paths to scan
* @param logger Logger instance
* @returns Scan results
*/
export async function scanArtifactsForTokens(
filesToScan: string[],
logger: Logger,
): Promise<void> {
logger.info(
"Starting best-effort check for potential GitHub tokens in debug artifacts (for testing purposes only)...",
);
const result: ScanResult = {
scannedFiles: 0,
findings: [],
};
// Create a temporary directory for extraction
const tempScanDir = fs.mkdtempSync(path.join(os.tmpdir(), "artifact-scan-"));
try {
for (const filePath of filesToScan) {
const stats = fs.statSync(filePath);
const fileName = path.basename(filePath);
if (stats.isDirectory()) {
const dirResult = await scanDirectory(filePath, fileName, logger);
result.scannedFiles += dirResult.scannedFiles;
result.findings.push(...dirResult.findings);
} else if (stats.isFile()) {
const fileResult = await scanFile(
filePath,
fileName,
tempScanDir,
logger,
);
result.scannedFiles += fileResult.scannedFiles;
result.findings.push(...fileResult.findings);
}
}
// Compute statistics from findings
const tokenTypesCounts = new Map<string, number>();
const filesWithTokens = new Set<string>();
for (const finding of result.findings) {
tokenTypesCounts.set(
finding.tokenType,
(tokenTypesCounts.get(finding.tokenType) || 0) + 1,
);
filesWithTokens.add(finding.filePath);
}
const tokenTypesSummary = Array.from(tokenTypesCounts.entries())
.map(([type, count]) => `${count} ${type}${count > 1 ? "s" : ""}`)
.join(", ");
const baseSummary = `scanned ${result.scannedFiles} files, found ${result.findings.length} potential token(s) in ${filesWithTokens.size} file(s)`;
const summaryWithTypes = tokenTypesSummary
? `${baseSummary} (${tokenTypesSummary})`
: baseSummary;
logger.info(`Artifact check complete: ${summaryWithTypes}`);
if (result.findings.length > 0) {
const fileList = Array.from(filesWithTokens).join(", ");
throw new Error(
`Found ${result.findings.length} potential GitHub token(s) (${tokenTypesSummary}) in debug artifacts at: ${fileList}. This is a best-effort check for testing purposes only.`,
);
}
} finally {
// Clean up temporary directory
try {
fs.rmSync(tempScanDir, { recursive: true, force: true });
} catch (e) {
logger.debug(
`Could not clean up temporary scan directory: ${getErrorMessage(e)}`,
);
}
}
}
You can’t perform that action at this time.