improvement(connectors): audit and harden all 30 knowledge base connectors

apps/sim/connectors/confluence/confluence.ts

@@ -1,6 +1,6 @@
 import { createLogger } from '@sim/logger'
 import { ConfluenceIcon } from '@/components/icons'
-import { fetchWithRetry } from '@/lib/knowledge/documents/utils'
+import { fetchWithRetry, VALIDATE_RETRY_OPTIONS } from '@/lib/knowledge/documents/utils'
 import type { ConnectorConfig, ExternalDocument, ExternalDocumentList } from '@/connectors/types'
 import { computeContentHash, htmlToPlainText, joinTagArray, parseTagDate } from '@/connectors/utils'
 import { getConfluenceCloudId } from '@/tools/confluence/utils'
@@ -243,43 +243,54 @@ export const confluenceConnector: ConnectorConfig = {
     const domain = sourceConfig.domain as string
     const cloudId = await getConfluenceCloudId(domain, accessToken)
 
-    const url = `https://api.atlassian.com/ex/confluence/${cloudId}/wiki/api/v2/pages/${externalId}?body-format=storage`
-
-    const response = await fetchWithRetry(url, {
-      method: 'GET',
-      headers: {
-        Accept: 'application/json',
-        Authorization: `Bearer ${accessToken}`,
-      },
-    })
+    // Try pages first, fall back to blogposts if not found
+    let page: Record<string, unknown> | null = null
+    for (const endpoint of ['pages', 'blogposts']) {
+      const url = `https://api.atlassian.com/ex/confluence/${cloudId}/wiki/api/v2/${endpoint}/${externalId}?body-format=storage`
+      const response = await fetchWithRetry(url, {
+        method: 'GET',
+        headers: {
+          Accept: 'application/json',
+          Authorization: `Bearer ${accessToken}`,
+        },
+      })
 
-    if (!response.ok) {
-      if (response.status === 404) return null
-      throw new Error(`Failed to get Confluence page: ${response.status}`)
+      if (response.ok) {
+        page = await response.json()
+        break
+      }
+      if (response.status !== 404) {
+        throw new Error(`Failed to get Confluence content: ${response.status}`)
+      }
     }
 
-    const page = await response.json()
-    const rawContent = page.body?.storage?.value || ''
+    if (!page) return null
+    const body = page.body as Record<string, unknown> | undefined
+    const storage = body?.storage as Record<string, unknown> | undefined
+    const rawContent = (storage?.value as string) || ''
     const plainText = htmlToPlainText(rawContent)
     const contentHash = await computeContentHash(plainText)
 
     // Fetch labels for this page
     const labelMap = await fetchLabelsForPages(cloudId, accessToken, [String(page.id)])
     const labels = labelMap.get(String(page.id)) ?? []
 
+    const links = page._links as Record<string, unknown> | undefined
+    const version = page.version as Record<string, unknown> | undefined
+
     return {
       externalId: String(page.id),
-      title: page.title || 'Untitled',
+      title: (page.title as string) || 'Untitled',
       content: plainText,
       mimeType: 'text/plain',
-      sourceUrl: page._links?.webui ? `https://${domain}/wiki${page._links.webui}` : undefined,
+      sourceUrl: links?.webui ? `https://${domain}/wiki${links.webui}` : undefined,
       contentHash,
       metadata: {
         spaceId: page.spaceId,
         status: page.status,
-        version: page.version?.number,
+        version: version?.number,
         labels,
-        lastModified: page.version?.createdAt,
+        lastModified: version?.createdAt,
       },
     }
   },
@@ -302,7 +313,25 @@ export const confluenceConnector: ConnectorConfig = {
 
     try {
       const cloudId = await getConfluenceCloudId(domain, accessToken)
-      await resolveSpaceId(cloudId, accessToken, spaceKey)
+      const spaceUrl = `https://api.atlassian.com/ex/confluence/${cloudId}/wiki/api/v2/spaces?keys=${encodeURIComponent(spaceKey)}&limit=1`
+      const response = await fetchWithRetry(
+        spaceUrl,
+        {
+          method: 'GET',
+          headers: {
+            Accept: 'application/json',
+            Authorization: `Bearer ${accessToken}`,
+          },
+        },
+        VALIDATE_RETRY_OPTIONS
+      )
+      if (!response.ok) {
+        return { valid: false, error: `Failed to validate space: ${response.status}` }
+      }
+      const data = await response.json()
+      if (!data.results?.length) {
+        return { valid: false, error: `Space "${spaceKey}" not found` }
+      }
       return { valid: true }
     } catch (error) {
       const message = error instanceof Error ? error.message : 'Failed to validate configuration'

apps/sim/connectors/github/github.ts

@@ -2,7 +2,7 @@ import { createLogger } from '@sim/logger'
 import { GithubIcon } from '@/components/icons'
 import { fetchWithRetry, VALIDATE_RETRY_OPTIONS } from '@/lib/knowledge/documents/utils'
 import type { ConnectorConfig, ExternalDocument, ExternalDocumentList } from '@/connectors/types'
-import { computeContentHash } from '@/connectors/utils'
+import { computeContentHash, parseTagDate } from '@/connectors/utils'
 
 const logger = createLogger('GitHubConnector')
 
@@ -82,7 +82,7 @@ async function fetchTree(
   const data = await response.json()
 
   if (data.truncated) {
-    logger.error('GitHub tree was truncated — some files may be missing', { owner, repo, branch })
+    logger.warn('GitHub tree was truncated — some files may be missing', { owner, repo, branch })
   }
 
   return (data.tree || []).filter((item: TreeItem) => item.type === 'blob')
@@ -139,7 +139,7 @@ async function treeItemToDocument(
     title: item.path.split('/').pop() || item.path,
     content,
     mimeType: 'text/plain',
-    sourceUrl: `https://github.com/${owner}/${repo}/blob/${branch}/${item.path}`,
+    sourceUrl: `https://github.com/${owner}/${repo}/blob/${encodeURIComponent(branch)}/${item.path.split('/').map(encodeURIComponent).join('/')}`,
     contentHash,
     metadata: {
       path: item.path,
@@ -302,6 +302,7 @@ export const githubConnector: ConnectorConfig = {
         throw new Error(`Failed to fetch file ${path}: ${response.status}`)
       }
 
+      const lastModifiedHeader = response.headers.get('last-modified') || undefined
       const data = await response.json()
       const content =
         data.encoding === 'base64'
@@ -314,14 +315,15 @@ export const githubConnector: ConnectorConfig = {
         title: path.split('/').pop() || path,
         content,
         mimeType: 'text/plain',
-        sourceUrl: `https://github.com/${owner}/${repo}/blob/${branch}/${path}`,
+        sourceUrl: `https://github.com/${owner}/${repo}/blob/${encodeURIComponent(branch)}/${path.split('/').map(encodeURIComponent).join('/')}`,
         contentHash,
         metadata: {
           path,
           sha: data.sha as string,
           size: data.size as number,
           branch,
           repository: `${owner}/${repo}`,
+          lastModified: lastModifiedHeader,
         },
       }
     } catch (error) {
@@ -400,6 +402,7 @@ export const githubConnector: ConnectorConfig = {
     { id: 'repository', displayName: 'Repository', fieldType: 'text' },
     { id: 'branch', displayName: 'Branch', fieldType: 'text' },
     { id: 'size', displayName: 'File Size', fieldType: 'number' },
+    { id: 'lastModified', displayName: 'Last Modified', fieldType: 'date' },
   ],
 
   mapTags: (metadata: Record<string, unknown>): Record<string, unknown> => {
@@ -414,6 +417,9 @@ export const githubConnector: ConnectorConfig = {
       if (!Number.isNaN(num)) result.size = num
     }
 
+    const lastModified = parseTagDate(metadata.lastModified)
+    if (lastModified) result.lastModified = lastModified
+
     return result
   },
 }

apps/sim/connectors/google-calendar/google-calendar.ts

@@ -439,6 +439,8 @@ export const googleCalendarConnector: ConnectorConfig = {
     { id: 'attendeeCount', displayName: 'Attendee Count', fieldType: 'number' },
     { id: 'location', displayName: 'Location', fieldType: 'text' },
     { id: 'eventDate', displayName: 'Event Date', fieldType: 'date' },
+    { id: 'lastModified', displayName: 'Last Modified', fieldType: 'date' },
+    { id: 'createdAt', displayName: 'Created', fieldType: 'date' },
   ],
 
   mapTags: (metadata: Record<string, unknown>): Record<string, unknown> => {
@@ -459,6 +461,12 @@ export const googleCalendarConnector: ConnectorConfig = {
     const eventDate = parseTagDate(metadata.eventDate)
     if (eventDate) result.eventDate = eventDate
 
+    const lastModified = parseTagDate(metadata.updatedTime)
+    if (lastModified) result.lastModified = lastModified
+
+    const createdAt = parseTagDate(metadata.createdTime)
+    if (createdAt) result.createdAt = createdAt
+
     return result
   },
 }

apps/sim/connectors/google-docs/google-docs.ts

@@ -162,7 +162,7 @@ function buildQuery(sourceConfig: Record<string, unknown>): string {
 
   const folderId = sourceConfig.folderId as string | undefined
   if (folderId?.trim()) {
-    parts.push(`'${folderId.trim()}' in parents`)
+    parts.push(`'${folderId.trim().replace(/'/g, "\\'")}' in parents`)
   }
 
   return parts.join(' and ')

apps/sim/connectors/google-drive/google-drive.ts

@@ -112,7 +112,7 @@ function buildQuery(sourceConfig: Record<string, unknown>): string {
 
   const folderId = sourceConfig.folderId as string | undefined
   if (folderId?.trim()) {
-    parts.push(`'${folderId.trim()}' in parents`)
+    parts.push(`'${folderId.trim().replace(/'/g, "\\'")}' in parents`)
   }
 
   const fileType = (sourceConfig.fileType as string) || 'all'

apps/sim/connectors/google-sheets/google-sheets.ts

@@ -2,11 +2,12 @@ import { createLogger } from '@sim/logger'
 import { GoogleSheetsIcon } from '@/components/icons'
 import { fetchWithRetry, VALIDATE_RETRY_OPTIONS } from '@/lib/knowledge/documents/utils'
 import type { ConnectorConfig, ExternalDocument, ExternalDocumentList } from '@/connectors/types'
-import { computeContentHash } from '@/connectors/utils'
+import { computeContentHash, parseTagDate } from '@/connectors/utils'
 
 const logger = createLogger('GoogleSheetsConnector')
 
 const SHEETS_API_BASE = 'https://sheets.googleapis.com/v4/spreadsheets'
+const DRIVE_API_BASE = 'https://www.googleapis.com/drive/v3/files'
 const MAX_ROWS = 10000
 const CONCURRENCY = 3
 
@@ -102,14 +103,47 @@ async function fetchSpreadsheetMetadata(
   return (await response.json()) as SpreadsheetMetadata
 }
 
+/**
+ * Fetches the spreadsheet's modifiedTime from the Drive API.
+ */
+async function fetchSpreadsheetModifiedTime(
+  accessToken: string,
+  spreadsheetId: string
+): Promise<string | undefined> {
+  try {
+    const url = `${DRIVE_API_BASE}/${encodeURIComponent(spreadsheetId)}?fields=modifiedTime&supportsAllDrives=true`
+    const response = await fetchWithRetry(url, {
+      method: 'GET',
+      headers: {
+        Authorization: `Bearer ${accessToken}`,
+        Accept: 'application/json',
+      },
+    })
+
+    if (!response.ok) {
+      logger.warn('Failed to fetch modifiedTime from Drive API', { status: response.status })
+      return undefined
+    }
+
+    const data = (await response.json()) as { modifiedTime?: string }
+    return data.modifiedTime
+  } catch (error) {
+    logger.warn('Error fetching modifiedTime from Drive API', {
+      error: error instanceof Error ? error.message : String(error),
+    })
+    return undefined
+  }
+}
+
 /**
  * Converts a single sheet tab into an ExternalDocument.
  */
 async function sheetToDocument(
   accessToken: string,
   spreadsheetId: string,
   spreadsheetTitle: string,
-  sheet: SheetProperties
+  sheet: SheetProperties,
+  modifiedTime?: string
 ): Promise<ExternalDocument | null> {
   try {
     const values = await fetchSheetValues(accessToken, spreadsheetId, sheet.title)
@@ -151,6 +185,7 @@ async function sheetToDocument(
         sheetId: sheet.sheetId,
         rowCount,
         columnCount: headers.length,
+        ...(modifiedTime ? { modifiedTime } : {}),
       },
     }
   } catch (error) {
@@ -208,7 +243,10 @@ export const googleSheetsConnector: ConnectorConfig = {
 
     logger.info('Fetching spreadsheet metadata', { spreadsheetId })
 
-    const metadata = await fetchSpreadsheetMetadata(accessToken, spreadsheetId)
+    const [metadata, modifiedTime] = await Promise.all([
+      fetchSpreadsheetMetadata(accessToken, spreadsheetId),
+      fetchSpreadsheetModifiedTime(accessToken, spreadsheetId),
+    ])
     const sheetFilter = (sourceConfig.sheetFilter as string) || 'all'
 
     let sheets = metadata.sheets.map((s) => s.properties)
@@ -226,7 +264,13 @@ export const googleSheetsConnector: ConnectorConfig = {
       const batch = sheets.slice(i, i + CONCURRENCY)
       const results = await Promise.all(
         batch.map((sheet) =>
-          sheetToDocument(accessToken, spreadsheetId, metadata.properties.title, sheet)
+          sheetToDocument(
+            accessToken,
+            spreadsheetId,
+            metadata.properties.title,
+            sheet,
+            modifiedTime
+          )
         )
       )
       documents.push(...(results.filter(Boolean) as ExternalDocument[]))
@@ -257,7 +301,22 @@ export const googleSheetsConnector: ConnectorConfig = {
       return null
     }
 
-    const metadata = await fetchSpreadsheetMetadata(accessToken, spreadsheetId)
+    let metadata: SpreadsheetMetadata
+    let modifiedTime: string | undefined
+    try {
+      ;[metadata, modifiedTime] = await Promise.all([
+        fetchSpreadsheetMetadata(accessToken, spreadsheetId),
+        fetchSpreadsheetModifiedTime(accessToken, spreadsheetId),
+      ])
+    } catch (error) {
+      const message = error instanceof Error ? error.message : String(error)
+      if (message.includes('404')) {
+        logger.info('Spreadsheet not found (possibly deleted)', { spreadsheetId })
+        return null
+      }
+      throw error
+    }
+
     const sheetEntry = metadata.sheets.find((s) => s.properties.sheetId === sheetId)
 
     if (!sheetEntry) {
@@ -269,7 +328,8 @@ export const googleSheetsConnector: ConnectorConfig = {
       accessToken,
       spreadsheetId,
       metadata.properties.title,
-      sheetEntry.properties
+      sheetEntry.properties,
+      modifiedTime
     )
   },
 
@@ -325,6 +385,7 @@ export const googleSheetsConnector: ConnectorConfig = {
     { id: 'sheetTitle', displayName: 'Sheet Name', fieldType: 'text' },
     { id: 'rowCount', displayName: 'Row Count', fieldType: 'number' },
     { id: 'columnCount', displayName: 'Column Count', fieldType: 'number' },
+    { id: 'lastModified', displayName: 'Last Modified', fieldType: 'date' },
   ],
 
   mapTags: (metadata: Record<string, unknown>): Record<string, unknown> => {
@@ -342,6 +403,11 @@ export const googleSheetsConnector: ConnectorConfig = {
       result.columnCount = metadata.columnCount
     }
 
+    const lastModified = parseTagDate(metadata.modifiedTime)
+    if (lastModified) {
+      result.lastModified = lastModified
+    }
+
     return result
   },
 }